Vulnerability database
Every flaw the U.S. government’s cybersecurity agency (CISA) has confirmed attackers are using, plus the new WordPress plugin and theme bugs published each day, sorted by what they mean for a small business. We refresh it twice a day. If you see something your website or office runs, tell us.
457 results · page 3 of 10
Jul 31, 2026Incorrect authorization in the http_request tool in Strands Agents Tools before 0.8.2 might allow remote attackers to obtain credentials configured via HTTP_REQCVE-2026-18394 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 6.9
Incorrect authorization in the http_request tool in Strands Agents Tools before 0.8.2 might allow remote attackers to obtain credentials configured via HTTP_REQUEST_TOKEN_CONFIG by influencing the LLM to route requests through actor-controlled proxy infrastructure. To remediate this issue, users should upgrade to version 0.8.2.
- Product
- Strands Agents Tools
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.comgithub.com
Jul 22, 2026n8n versions before 2.30.1 contain a privilege escalation vulnerability in the AI Agents feature where the node-execution tool lacks proper authorization checksCVE-2026-65015 · Other software · n8n-io · reported by VulnCheckHigh 7.2
n8n versions before 2.30.1 contain a privilege escalation vulnerability in the AI Agents feature where the node-execution tool lacks proper authorization checks. A Project Viewer user can escalate privileges by chatting with an agent that has node tools enabled, executing arbitrary nodes and accessing credential secrets without proper authorization verification.
- Product
- n8n
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Jul 20, 2026AgenticMail gives AI agents real email addresses and phone numbers.CVE-2026-57495 · Other software · agenticmail · reported by GitHubHigh 8.2
AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a privileged effect without verifying that the sender is the operator, while a sibling handler in the same repo does. The higher-impact one: any external email routed to the bridge inbox causes the dispatcher to resume the operator's Claude Code session with `permissionMode: 'bypassPermissions'`, embedding the attacker-controlled `from`/`subject`/`preview` verbatim into the prompt the resumed agent reads — an indirect prompt injection into a fully-privileged agent (Bash/Write/Edit/WebFetch + the agenticmail MCP toolbelt) running as the operator's OAuth identity. The sibling operator-query email-reply hook gates the same untrusted-From provenance with `isOperatorReplySender(replyFrom, config.operatorEmail)` (fail-closed); the bridge-wake path — a strictly higher-privilege effect — has no equivalent. @agenticmail/claudecode 0.2.39, @agenticmail/codex 0.1.33, @agenticmail/core 0.9.43, and @agenticma
- Product
- @agenticmail/core
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 20, 2026AgenticMail gives AI agents real email addresses and phone numbers.CVE-2026-57494 · Other software · agenticmail · reported by GitHubHigh 7.1
AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to `GET /api/agenticmail/tasks/pending?assignee=<name>`. The returned task objects include the task IDs and payloads. The same task IDs can then be used with the capability-style task mutation endpoints (`/tasks/:id/claim`, `/tasks/:id/result`, `/tasks/:id/complete`, `/tasks/:id/fail`) to claim, complete, or fail tasks assigned to a different agent. Because ordinary authenticated agents can discover agent names through `GET /api/agenticmail/accounts/directory`, the task ID effectively stops being a secret capability. This turns the intended capability model into a cross-agent authorization bypass. Version 0.9.64 contains a fix.
- Product
- @agenticmail/api
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 20, 2026AgenticMail gives AI agents real email addresses and phone numbers.CVE-2026-47255 · Other software · agenticmail · reported by GitHubHigh 8.2
AgenticMail gives AI agents real email addresses and phone numbers. @agenticmail/api prior to version 0.9.32 and @agenticmail/core prior to version 0.9.10 had weakness related to validation and and binding of inactive-agent hour filtering; storage SQL identifier validation; metadata-backed ownership checks for raw storage SQL; blocking direct storage metadata access through raw SQL; fail-closed outbound worker secret handling; SMTP envelope/header control-character validation before command construction; and TLS certificate verification as the default for MailSender with an explicit opt-out for local development. @agenticmail/api prior to version 0.9.32 and @agenticmail/core prior to version 0.9.10 are patched.
- Product
- @agenticmail/api
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 20, 2026nono is software that allows users to run AI agents in a zero-latency sandbox.CVE-2026-47128 · Other software · always-further · reported by GitHubMedium 6.1
nono is software that allows users to run AI agents in a zero-latency sandbox. Prior to version 0.55.0, the nono Landlock/seccomp policies allow access to local Unix domain sockets (concrete and abstract). This allows an easy sandbox escape by talking to the per-user systemd dbus socket. Version 0.55.0 patches the issue.
- Product
- nono
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 16, 2026The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store.CVE-2026-46341 · Other software · apify · reported by GitHubMedium 6.1
The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store. Prior to 0.9.21, the fetch-apify-docs tool in src/tools/common/fetch_apify_docs.ts validates allowlisted documentation domains with String.startsWith() rather than URL hostname comparison, allowing attacker-controlled URLs such as `https://docs.apify.com.evil.com/` and `https://docs.apify.com@evil.com/` to pass the ALLOWED_DOC_DOMAINS check and return arbitrary fetched content to the LLM. This issue is fixed in version 0.9.21.
- Product
- apify-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 16, 2026AWS Bedrock AgentCore Python SDK is an open-source Python library that provides client tools for building AI agents on the Amazon Bedrock AgentCore platform.CVE-2026-15737 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 5.7
AWS Bedrock AgentCore Python SDK is an open-source Python library that provides client tools for building AI agents on the Amazon Bedrock AgentCore platform. Unintended logging of sensitive user content in the OpenTelemetry instrumentation in AWS Bedrock AgentCore Python SDK versions 1.4.8 and 1.5.0 might allow a local authenticated user with access to CloudWatch Logs to access raw user prompts and agent responses containing sensitive data via span attributes. The SDK wrote raw user prompts and complete agent responses into OpenTelemetry span attributes on every invocation without filtering or masking. These spans flow into the customer's aws/spans CloudWatch log group, exposing sensitive content to any principal with log read access. We recommend you upgrade to version 1.5.1 or later. Users who ran affected versions should also review and purge sensitive content from their aws/spans CloudWatch log groups.
- Product
- bedrock-agentcore
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.comgithub.com
Jul 15, 2026Strands Agents is an open-source Python SDK for building and running AI agents.CVE-2026-15746 · Other software · Amazon · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 6.9
Strands Agents is an open-source Python SDK for building and running AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the elasticsearch_memory tool for agent memory storage. We identified CVE-2026-15746, a server-side request forgery (SSRF) issue in the elasticsearch_memory tool. The tool exposed its connection parameters (es_url, cloud_id, api_key) as fields the large language model (LLM) could control through the tool schema. When a caller omitted the api_key parameter, the tool fell back to the operator's ELASTICSEARCH_API_KEY environment variable and sent it to whichever host the LLM specified. A crafted prompt could cause the tool to connect to a threat-actor-controlled server and disclose the operator's Elasticsearch API key in the Authorization header. We recommend you upgrade to strands-agents-tools version 0.7.0 or later. As a precautionary measure, we recommend all operators rotate their ELASTICSEARCH_API_KEY, even if there is no indication the credential was exposed.
- Product
- strands-agents-tools
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.comgithub.com
Jul 15, 2026PraisonAI (praisonaiagents) before 1.6.78 contains a remote code execution vulnerability in the plugin manager, which loads and executes arbitrary Python (.py) CVE-2026-61446 · Other software · MervinPraison · reported by VulnCheckHigh 8.6
PraisonAI (praisonaiagents) before 1.6.78 contains a remote code execution vulnerability in the plugin manager, which loads and executes arbitrary Python (.py) files from project-level and user-home .praisonai/plugins/ directories using importlib spec_from_file_location() and exec_module() without code signing, integrity verification, or sandboxing. An attacker who can write a malicious .py file to a plugin directory (for example via path traversal, a supply chain attack, or a compromised dependency) achieves arbitrary code execution when the plugin system initializes.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Jul 13, 2026OpenBMB XAgent v1.0.0 and before is vulnerable to path traversal in the file() function in XAgent/XAgentServer/application/routers/workspace.py.CVE-2026-26396 · Other software · reported by MITREHigh 7.5
OpenBMB XAgent v1.0.0 and before is vulnerable to path traversal in the file() function in XAgent/XAgentServer/application/routers/workspace.py. The input parameter “filename” is user-controllable and is concatenated into the file path to be read without proper validation, leading to a directory traversal vulnerability that may result in sensitive information disclosure.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgist.github.comgist.github.com
Jul 11, 2026PraisonAI Platform (praisonai-platform) before 0.1.9 fails to enforce owner/admin authorization on the PATCH routes for projects, issues, and agents, which onlyCVE-2026-61442 · Other software · MervinPraison · reported by VulnCheckHigh 7.1
PraisonAI Platform (praisonai-platform) before 0.1.9 fails to enforce owner/admin authorization on the PATCH routes for projects, issues, and agents, which only require workspace-member role. A workspace member can modify owner-created records; for projects, a member can reassign lead_id to their own user id and then delete the owner-created project, bypassing the delete route's owner/admin permission check.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 10, 2026Incorrect Authorization vulnerability in Drupal AI Agents allows Forceful Browsing.CVE-2026-13237 · Websites & servers · reported by mlhess@drupal.orgMedium 4.8
Incorrect Authorization vulnerability in Drupal AI Agents allows Forceful Browsing. This issue affects AI Agents versions: from 0.0.0 to 1.1.4, from 1.2.0 to 1.2.5, from 1.3.0 to 1.3.1.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 10, 2026Missing Authorization vulnerability in Drupal AI Agents allows Forceful Browsing.CVE-2026-13236 · Websites & servers · reported by mlhess@drupal.orgMedium 4.2
Missing Authorization vulnerability in Drupal AI Agents allows Forceful Browsing. This issue affects AI Agents versions: from 0.0.0 to 1.1.4, from 1.2.0 to 1.2.5, from 1.3.0 to 1.3.1.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 10, 2026EverOS is a memory runtime for agents.CVE-2026-58499 · Other software · EverMind-AI · reported by GitHubHigh 8.2
EverOS is a memory runtime for agents. Prior to 1.0.1, EverOS is vulnerable to path traversal in the POST /api/v1/memory/add ingestion endpoint because the per-message sender_id field was not validated as a path-safe identifier, unlike app_id and project_id. During user-memory extraction, sender_id is used as owner_id and joined into the filesystem path where the extracted episode is persisted as a Markdown file, so a sender_id containing ../ sequences could direct writes outside the configured memory root and allow an unauthenticated caller to create or overwrite .md files at locations writable by the server process with partially attacker-influenced content. This issue is fixed in version 1.0.1.
- Product
- EverOS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 10, 2026PraisonAI versions before 4.6.78 contain a code injection vulnerability in deploy/api.py where the agents_file parameter is directly interpolated into an f-striCVE-2026-61444 · Other software · MervinPraison · reported by VulnCheckCritical 9.4
PraisonAI versions before 4.6.78 contain a code injection vulnerability in deploy/api.py where the agents_file parameter is directly interpolated into an f-string without sanitization. Attackers can inject arbitrary Python code that executes when the generated server code runs via subprocess.Popen().
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Jul 10, 2026PraisonAI (pip package praisonaiagents) before 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow._resolve_pydantic_class (src/praisonaCVE-2026-61437 · Other software · MervinPraison · reported by VulnCheckHigh 8.5
PraisonAI (pip package praisonaiagents) before 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow._resolve_pydantic_class (src/praisonai-agents/praisonaiagents/workflows/workflows.py). When a workflow step uses a string output_pydantic reference, the framework locates and imports a sibling tools.py from the workflow file's directory via importlib exec_module without sandboxing, ignoring the PRAISONAI_ALLOW_*_TOOLS environment variables. An attacker who controls a workflow file and its sibling tools.py can execute arbitrary Python code with the workflow runner's privileges when the workflow is executed via WorkflowManager or after load_yaml.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Jul 10, 2026PraisonAI (praisonaiagents) before 1.6.78 contains a path traversal vulnerability in the FastContext feature (praisonaiagents.context.fast).CVE-2026-61432 · Other software · MervinPraison · reported by VulnCheckMedium 6.9
PraisonAI (praisonaiagents) before 1.6.78 contains a path traversal vulnerability in the FastContext feature (praisonaiagents.context.fast). FastContextAgent.execute_tool() prepends the configured workspace_path only for relative paths and neither rejects absolute paths nor canonicalizes joined paths before enforcing workspace containment. As a result, tool arguments or model-generated function calls to grep_search, glob_search, read_file, or list_directory can supply absolute paths or '../' traversal sequences to read, search, and enumerate files outside the intended workspace directory, with file contents returned to the caller or injected into the model's tool-result context.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 10, 2026PraisonAI (pip package praisonaiagents) before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and dCVE-2026-60089 · Other software · MervinPraison · reported by VulnCheckMedium 6.9
PraisonAI (pip package praisonaiagents) before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and does not validate the defaults.output.output_file path. A repository-controlled config file can set output_file to an absolute or '..' traversal path; when the developer subsequently calls agent.start() without explicitly passing an output parameter, PraisonAI writes the agent response to that path (creating parent directories as needed), allowing an untrusted checked-out project to overwrite files outside the project root with the privileges of the user running PraisonAI.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 10, 2026Improper access control in SamsungSEAgentService prior to SMR Jul-2026 Release 1 allows local attackers to access sensitive information.CVE-2026-21041 · Computers, phones & browsers · Samsung Mobile · reported by mobile.security@samsung.comMedium 6.9
Improper access control in SamsungSEAgentService prior to SMR Jul-2026 Release 1 allows local attackers to access sensitive information.
- Product
- Samsung Mobile Devices
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordsecurity.samsungmobile.com
Jul 9, 2026Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents.CVE-2026-54695 · Other software · pipecat-ai · reported by GitHubHigh 7.5
Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents. Prior to 1.4.0, the pipecat development runner registers a /ws WebSocket endpoint for telephony testing that accepts connections without authentication, reads an attacker-supplied callSid from a Twilio stream-start handshake in src/pipecat/runner/utils.py, and passes it to TwilioFrameSerializer so the server can issue an authenticated Twilio REST API hang-up request with the server operator's credentials; equivalent unauthenticated call-control sinks exist for Telnyx and Plivo. This issue is fixed in version 1.4.0.
- Product
- pipecat
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 26, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2026-56823 · Other software · Significant-Gravitas · reported by GitHubMedium 5.4
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to , the `POST /api/integrations/webhooks/{webhook_id}/ping` endpoint fetches the target webhook by primary key alone without verifying that the webhook belongs to the authenticated user. Any authenticated user can supply an arbitrary webhook_id to confirm webhook existence, leak the webhook's OAuth provider type, and in some cases trigger a ping delivery on behalf of another user. This vulnerability is fixed in .
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 26, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2026-56663 · Other software · Significant-Gravitas · reported by GitHubHigh 8.5
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.52, an authenticated user can bypass the SSRF / private-IP protections in SendWebRequestBlock and reach internal network services. _is_ip_blocked() in backend/backend/util/request.py does not normalize IPv4-mapped IPv6 addresses before checking resolved IPs against the blocked IPv4 ranges, and does not block special-use ranges such as 100.64.0.0/10 (CGNAT, RFC 6598). A hostname that resolves to an IPv4-mapped IPv6 address therefore passes validation and the request reaches the embedded internal IPv4 endpoint. This affects all AutoGPT Platform deployments. This vulnerability is fixed in 0.6.52.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 26, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2025-32423 · Other software · Significant-Gravitas · reported by GitHubMedium 5.3
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in ExtractTextInformationBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the server will consume 50G of memory, eventually causing memory resources to be exhausted, resulting in DoS. This vulnerability is fixed in 0.6.32.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 26, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2025-32394 · Other software · Significant-Gravitas · reported by GitHubMedium 5.3
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the server will consume 50G of memory, eventually causing memory resources to be exhausted, resulting in DoS. This vulnerability is fixed in 0.6.32.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 25, 2026ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI agents.CVE-2026-55413 · Other software · ToolJet · reported by GitHubCritical 9.4
ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI agents. Prior to 3.20.178-lts, any authenticated user with builder role (free tier) can overwrite a globally-shared marketplace plugin with arbitrary JavaScript that executes server-side with full Node.js access (require, process). The malicious code runs whenever any user on the instance triggers a query using that plugin — achieving both RCE and supply-chain compromise of the entire ToolJet deployment. This vulnerability is fixed in 3.20.178-lts.
- Product
- ToolJet
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 25, 2026ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI agents.CVE-2026-55412 · Other software · ToolJet · reported by GitHubHigh 8.3
ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI agents. Prior to 3.20.178-lts, there's an SSRF in the RestAPI data source component. The RestAPI data source executes HTTP requests server-side, and its private IP filter only checks the hostname string — not the resolved IP. DNS names like 169.254.169.254.nip.io resolve to the Azure IMDS link-local address and bypass the filter entirely. This allows any authenticated user (free tier) to steal Azure managed identity tokens for the AKS production cluster. This vulnerability is fixed in 3.20.178-lts.
- Product
- ToolJet
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 25, 2026ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI agents.CVE-2026-55411 · Other software · ToolJet · reported by GitHubMedium 6.8
ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI agents. Prior to 3.20.1780-lts, the authenticated endpoint POST /api/data-sources/decrypt returns the decrypted plaintext for any credential whose credential_id is supplied in the request body. Unlike every neighbouring data-source route, this handler is not protected by ValidateDataSourceGuard, does not receive the calling @User(), and the underlying CredentialsService.getValue() looks the credential up by id only, with no organization scoping. As a result, any authenticated user of any organization can decrypt the data-source secrets of any other organization by supplying that organization's credential_id — a cross-tenant confidentiality breach. This vulnerability is fixed in 3.20.1780-lts.
- Product
- ToolJet
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 24, 2026Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser.CVE-2026-53766 · Other software · ChromeDevTools · reported by GitHubMedium 6.1
Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser. From 0.24.0 until 1.1.0, McpContext.validatePath() enforces workspace roots by checking whether path.resolve(filePath) textually falls under one of the configured root paths. path.resolve() does not canonicalize symbolic links. As a result, a symlink inside a configured workspace root can point to a file outside that root, pass validation, and then be followed by downstream file read/write operations. This bypass applies even when the MCP client correctly declares the roots capability with a non-empty list. It is separate from the documented legacy behavior where missing roots capability allows all paths. The practical impact is a workspace-boundary bypass. In the write direction, filePath-writing tools can overwrite out-of-root files through an in-root symlink. In the read direction, upload_file can read through the symlink and send the file to the currently selected web page. This vulnerability is fixed in 1.1.0.
- Product
- chrome-devtools-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 24, 2026Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser.CVE-2026-53765 · Other software · ChromeDevTools · reported by GitHubMedium 6.1
Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser. From 0.20.0 until 1.1.0, The chrome-devtools-mcp daemon writes its PID file with fs.writeFileSync() to a deterministic runtime path. On typical macOS environments, and on Linux sessions where $XDG_RUNTIME_DIR is unset, that runtime path falls back to /tmp/chrome-devtools-mcp-<uid>/daemon.pid. Because the write does not use O_NOFOLLOW, a local low-privilege user on the same POSIX host can pre-create /tmp/chrome-devtools-mcp-<victim_uid>/daemon.pid as a symlink to a file writable by the victim. When the victim later starts daemon mode, fs.writeFileSync() follows the symlink and truncates the target file to the daemon PID string. This vulnerability is fixed in 1.1.0.
- Product
- chrome-devtools-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 24, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2026-33235 · Other software · Significant-Gravitas · reported by GitHubHigh 7.7
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and "noisy neighbor" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-55450 · Other software · langflow-ai · reported by GitHubCritical 9.3
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.1, unauthenticated users can upload any amount of data to the server without any limitations. No need for any prior knowledge, only network access to Langflow. This can lead to space exhaustion on the server. In addition, in the response, the absolute path of the uploaded file is reported to the attacker, which is an information leak that can assist in chaining other primitives. This vulnerability is fixed in 1.9.1.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-55447 · Other software · langflow-ai · reported by GitHubCritical 9.6
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.2, by controlling a files that are digested into the RAG, an attacker can direct the node to read any file on the file-system by absolute path. All components based on BaseFileComponent are vulnerable to the vulnerability. This includes Docling (DoclingInlineComponent), Docling Serve, DoclingRemoteComponent), Read File (FileComponent), NVIDIA Retriever Extraction (NvidiaIngestComponent), Video File (VideoFileComponent), and Unstructured API (UnstructuredComponent). This vulnerability is fixed in 1.9.2.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-55446 · Other software · langflow-ai · reported by GitHubHigh 7.5
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.0.19, an attacker can send a /api/v1/files/upload/ request without any authentication token/cookies and abuse a very long multipart form boundary to make the langflow app unusable for all users for an indefinite amount of time. This vulnerability is fixed in 1.0.19.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-55423 · Other software · langflow-ai · reported by GitHubMedium 6.1
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.7.0, the logout button does not clear the session. The previous user stays logged in unless another user explicitly logs in. This vulnerability is fixed in 1.7.0.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-48520 · Other software · langflow-ai · reported by GitHubMedium 6.1
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.10.0, the "Shareable Playground" (or "Public Flows" in code) contains a potential arbitrary file-read vulnerability, depending on the exact flow configuration used. By making a flow public, public execution of the flow is allowed. The execution request can contain a list of files that gets read by Langflow and fed into the LLM. The files path can be any path supported by the storage - it can be either a local file or S3 path if supported by the local configuration This vulnerability is fixed in 1.10.0.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-48519 · Other software · langflow-ai · reported by GitHubCritical 9.6
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.2, the "Shareable Playground" (or "Public Flows" in code) contains a critical RCE vulnerability. Shareable Playground feature works by enabling the execution of workflows by unauthenticated users, by accessing a link. Specifically, it enables the route /api/v1/build_public_tmp to execute any public flow, given a public flow ID. When the route executes the flow, it allows for providing arbitrary custom Python code as the nodes code, inside the JSON payload. The vulnerable field is data.nodes[X].data.node.template.code.value. This vulnerability is fixed in 1.9.2.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-42867 · Other software · langflow-ai · reported by GitHubMedium 6.5
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, Langflow is vulnerable to Path Traversal in the Knowledge Bases API (POST /api/v1/knowledge_bases). This occurs because user-supplied knowledge base names are used directly to create file paths without proper sanitization or containment checks. An authenticated attacker can exploit this flaw to create directories and write files anywhere on the server's filesystem. This vulnerability is fixed in 1.9.0.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026Langflow is a tool for building and deploying AI-powered agents and workflows.CVE-2026-33760 · Other software · langflow-ai · reported by GitHubHigh 8.8
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, Langflow's /api/v1/monitor router exposes 7 endpoints that perform read, write, and delete operations on user-owned resources — messages, sessions, build artifacts, and LLM transaction logs — without verifying that the authenticated requester owns the targeted resource. Any authenticated user can read, modify, rename, or permanently delete another user's data by supplying the target's resource ID or flow_id. This is a classic IDOR/BOLA vulnerability. Notably, the same source file (monitor.py) contains one correctly-implemented endpoint that uses an ownership check, demonstrating the correct pattern was known but inconsistently applied. This vulnerability is fixed in 1.9.0.
- Product
- langflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026NanoClaw before 2.1.17 contains a symlink following vulnerability in forwardAttachedFiles that allows container-controlled agents to exfiltrate host-readable fiCVE-2026-56692 · Other software · nanocoai · reported by VulnCheckMedium 6.8
NanoClaw before 2.1.17 contains a symlink following vulnerability in forwardAttachedFiles that allows container-controlled agents to exfiltrate host-readable files. The host validates attachment filenames using only isSafeAttachmentName before copying with fs.copyFileSync, which follows symlinks without containment checks, allowing malicious agents to disclose arbitrary host files.
- Product
- nanoclaw
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026LangChain is a framework for building agents and LLM-powered applications.CVE-2026-55443 · Other software · langchain-ai · reported by GitHubMedium 5.1
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search agent middleware that validates a starting directory but not the search pattern or the resolved target of matched files, so glob patterns and symlinks can reach files outside the configured root; prompt- and chain/agent-configuration loaders that accept path fields and resolve them without confining the result to a trusted base or rejecting symlink targets; and path-prefix authorization checks that compare by string prefix without a path-segment boundary, so a sibling path sharing the prefix is accepted. When these components receive path values, search patterns, or workspace contents influenced by an untrusted source — including an LLM acting on untrusted input — the result can be disclosure of files outside the intended boundary. This vulnerability is fixed in 1.3.9.
- Product
- langchain
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2026-55237 · Other software · Significant-Gravitas · reported by GitHubHigh 8.8
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions prior to 0.6.62 have a DOM-based Cross-Site Scripting (XSS) vulnerability in AutoGPT's signup page. The application improperly trusts a URL parameter (`next`), which is passed to `router.push`. An attacker can craft a malicious link that, when opened by an authenticated user, performs a client-side redirect and executes arbitrary JavaScript in the context of their browser. This could lead to credential theft, internal network pivoting, and unauthorized actions performed on behalf of the victim. Version 0.6.62 patches the issue.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2025-32437 · Other software · Significant-Gravitas · reported by GitHubHigh 8.7
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, `MediaDurationBlock` will download and store the video in a temporary directory without deleting before all noded are done. `StepThroughItemsBlock` can be used to iterate `MediaDurationBlock` multiple times. `StepThroughItemsBlock` does not limit the number of loops. In addition, `MediaDurationBlock ` does not limit the amount of disk space consumed in the current working directory and does not delete the video after outputing the result. When a malicious user chooses to screen shot many web pages, the disk space will eventually run out, causing a DoS. Version 0.6.63 patches the issue.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2025-32436 · Other software · Significant-Gravitas · reported by GitHubHigh 7.1
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, `AddAudioToVideoBlock` will download and store the video and audio in a temporary directory without deleting before all noded are done. `StepThroughItemsBlock` can be used to iterate `MediaDurationBlock` multiple times. `StepThroughItemsBlock` does not limit the number of loops. In addition, `AddAudioToVideoBlock` does not limit the amount of disk space consumed in the current working directory and does not delete the video after outputing the result. When a malicious user chooses to screen shot many web pages, the disk space will eventually run out, causing a DoS. Version 0.6.63 patches the issue.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2025-32424 · Other software · Significant-Gravitas · reported by GitHubHigh 8.7
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, ScreenshotWebPageBlock will store the captured screenshots in a temporary directory. `StepThroughItemsBlock` can be used to iterate `ScreenshotWebPageBlock` multiple times. `StepThroughItemsBlock` does not limit the number of loops. In addition, `ScreenshotWebPageBlock` does not limit the amount of disk space consumed in the current working directory. When a malicious user chooses to screen shot many web pages, the disk space will eventually run out, causing a DoS. Version 0.6.63 patches the issue.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2025-32422 · Other software · Significant-Gravitas · reported by GitHubHigh 8.7
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, `StepThroughItemsBlock` can iterate all the contents in a list and send them to `FileStoreBlock` for downloading one by one. Although `FileStoreBlock` has access time limits for downloading files, `StepThroughItemsBlock` can be used to slowly iterate and download relatively small files (e.g., 100M) multiple times. `StepThroughItemsBlock` does not limit the number of loops. In addition, `FileStoreBlock` does not limit the amount of disk space consumed in the current working directory. When a malicious user chooses to download too many videos, the disk space will eventually run out, causing a DoS. Version 0.6.63 patches the issue.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents.CVE-2025-32392 · Other software · Significant-Gravitas · reported by GitHubHigh 8.7
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, AutoGPT's LoopVideoBLock allows users to input a video file and process the video, such as looping it 5 times or extending the time, and finally writing it to disk. However, there is no limit on the resources that can be allocated during execution. For example, the number of loops is user-controllable and unlimited. When a malicious attacker loops too many times, the generated video is too large, and after writing it to disk, the disk space is exhausted, eventually causing DoS. Version 0.6.63 patches the issue.
- Product
- AutoGPT
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 17, 2026Windows-MCP is an open-source project that integrates AI agents with Windows.CVE-2026-48989 · Other software · CursorTouch · reported by GitHubHigh 8.9
Windows-MCP is an open-source project that integrates AI agents with Windows. In versions prior to 0.7.5, certain HTTP modes exposed the MCP control plane without authentication while enabling wildcard CORS (allow_origins=*, allow_methods=*, allow_headers=*). Because the same server also exposed a PowerShell tool that executes caller-controlled commands as the Windows user running Windows-MCP, attackers could reach the control plane from arbitrary origins or non-browser clients and achieve arbitrary PowerShell execution. This issue was fixed in version 0.7.5.
- Product
- Windows-MCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 12, 2026AgenticMail gives AI agents real email addresses and phone numbers.CVE-2026-50287 · Other software · agenticmail · reported by GitHubHigh 8.7
AgenticMail gives AI agents real email addresses and phone numbers. Prior to version 0.9.27, @agenticmail/mcp exposes a Streamable HTTP transport when started with --http or MCP_HTTP=1. In that mode, the /mcp endpoint accepts requests without any HTTP authentication layer. A remote client can initialize a session and call tools directly. This issue has been patched in version 0.9.27.
- Product
- agenticmail
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 9, 2026Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents.CVE-2026-44716 · Other software · pipecat-ai · reported by GitHubHigh 7.5
Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents. From version 0.0.90 to before version 1.2.0, a path traversal vulnerability exists in Pipecat's development runner (src/pipecat/runner/run.py). When the runner is started with the --folder flag, it exposes a GET /files/{filename:path} download endpoint. The filename path parameter is concatenated directly onto args.folder with no containment check. Starlette normalises literal ../ sequences in URLs, but %2F-encoded slashes bypass this normalisation: the path parameter is URL-decoded after routing, so ..%2F..%2Fetc%2Fpasswd resolves to a path two levels above args.folder. An attacker with network access to the runner can read any file the pipecat process has permission to access — including SSH private keys, credentials, and system files — with a single unauthenticated HTTP request. This issue has been patched in version 1.2.0.
- Product
- pipecat
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Where this comes from: the exploited list is CISA’s Known Exploited Vulnerabilities catalog. Everything else is the whole National Vulnerability Database, where each record is published by the team that found the bug (Wordfence, Patchstack, WPScan, the vendors themselves and others); we show who. Exploit odds are FIRST’s EPSS, updated daily. Titles and categories are ours, so check the linked record before acting on a detail. For a write-up of the big ones, see our advisories. Every vendor, and every WordPress plugin and theme with a recorded flaw, also has its own page. All of it is free to reuse as JSON, CSV or RSS.
Weekly security brief
The flaws that hit local websites, every Friday.
One short email: what got exploited this week, which WordPress plugins broke, and what to check. Unsubscribe in one click.
Tell us what you're building.
A website, your marketing, a security check, an app, or the thing you've been running out of a spreadsheet for three years. A few lines is plenty.
Not ready to talk yet? Run the free website check and see what Google sees.