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.
3,489 results · page 9 of 70
Sep 3, 2026A vulnerability was detected in 2FastLabs agent-squad up to 1.1.4.CVE-2026-85100 · Other software · 2FastLabs · reported by VulDBLow 2.1
A vulnerability was detected in 2FastLabs agent-squad up to 1.1.4. Affected by this vulnerability is the function AgentSquad.routeRequest of the file agent-squad/typescript/src/orchestrator.ts of the component Streaming Agent Response Workflow. The manipulation results in resource consumption. It is possible to launch the attack remotely. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- agent-squad
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 3, 2026Dell PowerProtect Data Manager, versions 20.2.0.0 and below, contain a stack buffer overflow vulnerability in file-level restore agent.CVE-2026-73600 · Other software · Dell · reported by security_alert@emc.comHigh 7.8
Dell PowerProtect Data Manager, versions 20.2.0.0 and below, contain a stack buffer overflow vulnerability in file-level restore agent. A high privileged remote attacker could potentially exploit this vulnerability, leading to Information disclosure.
- Product
- PowerProtect Data Manager
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 3, 2026A vulnerability was identified in simular-ai Agent-S up to 0.3.2.CVE-2026-84887 · Other software · simular-ai · reported by VulDBLow 2.1
A vulnerability was identified in simular-ai Agent-S up to 0.3.2. Affected by this issue is some unknown functionality of the file grounding.py of the component Model-generated GUI Action Execution Workflow. The manipulation leads to denial of service. Remote exploitation of the attack is possible. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- Agent-S
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 3, 2026A vulnerability was determined in simular-ai Agent-S up to 0.3.2.CVE-2026-84886 · Other software · simular-ai · reported by VulDBMedium 5.5
A vulnerability was determined in simular-ai Agent-S up to 0.3.2. Affected by this vulnerability is the function ImageData of the file gui_agents/s1/utils/ocr_server.py of the component OCR HTTP API. Executing a manipulation of the argument img_bytes can lead to resource consumption. The attack may be launched remotely. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- Agent-S
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 3, 2026A vulnerability has been found in simular-ai Agent-S 0.3.1/0.3.2.CVE-2026-84885 · Other software · simular-ai · reported by VulDBLow 2.1
A vulnerability has been found in simular-ai Agent-S 0.3.1/0.3.2. This impacts an unknown function of the file code_agent.py of the component CodeAgent. Such manipulation leads to denial of service. The attack can be launched remotely. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- Agent-S
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 2, 2026agentverus-scanner fails to analyze compiled Python bytecode files in companion code directories, allowing attackers to bypass security scanning by shipping malCVE-2026-84811 · Other software · agentverus · reported by VulnCheckHigh 7.1
agentverus-scanner fails to analyze compiled Python bytecode files in companion code directories, allowing attackers to bypass security scanning by shipping malicious __pycache__ entries alongside benign source files. Attackers can execute arbitrary Python bytecode on import while the scanner reports a CERTIFIED verdict with high trust scores in both static and semantic analysis modes.
- Product
- agentverus-scanner
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 2, 2026In Jenkins 2.579 and earlier, LTS 2.568.2 and earlier, the REST API and CLI endpoints for updating agent configuration do not prevent a submitted configuration CVE-2026-84651 · Websites & servers · Jenkins Project · reported by jenkinsci-cert@googlegroups.comMedium 6.3
In Jenkins 2.579 and earlier, LTS 2.568.2 and earlier, the REST API and CLI endpoints for updating agent configuration do not prevent a submitted configuration from overwriting a different agent by specifying that agent's name in the submitted XML document, allowing attackers with Agent/Configure permission on one agent to take over a different agent, gaining control of its configuration and obtaining access to its inbound agent secret and environment variables.
- Product
- Jenkins
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 2, 2026Incorrect Permission Assignment for Critical Resource (CWE-732) in Elastic Agent can lead to local privilege escalation via Replace Binaries (CAPEC-642).CVE-2026-78604 · Other software · Elastic · reported by security@elastic.coHigh 7.8
Incorrect Permission Assignment for Critical Resource (CWE-732) in Elastic Agent can lead to local privilege escalation via Replace Binaries (CAPEC-642). On Windows systems where Elastic Agent is installed in unprivileged mode, resources used by the agent service are created with access controls broader than required. A local user could take advantage of this to cause the service to execute code of their choosing, ultimately obtaining SYSTEM-level privileges on the host.
- Product
- Elastic Agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 2, 2026Incorrect Authorization (CWE-863) in Fleet Server can lead to a denial of service of agent upload operations via Privilege Abuse (CAPEC-122).CVE-2026-78587 · Other software · Elastic · reported by security@elastic.coLow 3.1
Incorrect Authorization (CWE-863) in Fleet Server can lead to a denial of service of agent upload operations via Privilege Abuse (CAPEC-122). Fleet Server does not correctly verify session ownership during multi-part data upload operations, allowing any authenticated agent to interfere with the active upload sessions belonging to other enrolled agents.
- Product
- Fleet Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 1, 2026A vulnerability was determined in zhayujie CowAgent up to 2.1.7.CVE-2026-84427 · Other software · zhayujie · reported by VulDBLow 2.1
A vulnerability was determined in zhayujie CowAgent up to 2.1.7. Affected is an unknown function of the file agent/tools/bash/bash.py of the component Bash Tool. Executing a manipulation can lead to denial of service. The attack can be launched remotely. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- CowAgent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 1, 2026A vulnerability was found in zhayujie CowAgent up to 2.1.3.CVE-2026-84425 · Other software · zhayujie · reported by VulDBLow 2.1
A vulnerability was found in zhayujie CowAgent up to 2.1.3. This impacts the function BrowserTool of the file agent/tools/browser/browser_tool.py of the component Browser Tool. Performing a manipulation results in denial of service. The attack can be initiated remotely. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- CowAgent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 1, 2026WWBN AVideo (current e01e41ecc and earlier) makes three login-time security controls depend solely on the client-supplied User-Agent header.CVE-2026-84479 · Other software · WWBN · reported by VulnCheckCritical 9.3
WWBN AVideo (current e01e41ecc and earlier) makes three login-time security controls depend solely on the client-supplied User-Agent header. The isAVideoEncoder()/isAVideoMobileApp() checks match HTTP_USER_AGENT against a hardcoded literal ("AVideoEncoder"/"AVideoMobileApp") with no IP check or shared secret. An attacker who submits valid credentials and sets User-Agent: AVideoEncoder bypasses two-factor authentication, skips brute-force captcha escalation, and avoids being recorded in the login/device audit history. No patch is available at the time of publication.
- Product
- AVideo
- 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
Sep 1, 2026A vulnerability was found in NousResearch hermes-agent up to 0.18.2.CVE-2026-84289 · Other software · NousResearch · reported by VulDBLow 2.1
A vulnerability was found in NousResearch hermes-agent up to 0.18.2. This vulnerability affects the function list_tools of the file tools/mcp_tool.py of the component MCP Tool. Performing a manipulation results in uncontrolled memory allocation. It is possible to initiate the attack remotely. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- hermes-agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 1, 2026A vulnerability has been found in NousResearch hermes-agent up to 0.18.2.CVE-2026-84288 · Other software · NousResearch · reported by VulDBLow 2.1
A vulnerability has been found in NousResearch hermes-agent up to 0.18.2. This affects the function HermesACPAgent.prompt of the file acp_adapter/session.py of the component ACP Prompt Workflow. Such manipulation leads to denial of service. The attack may be performed from remote. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- hermes-agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 1, 2026A flaw has been found in NousResearch hermes-agent 0.18.0.CVE-2026-84287 · Other software · NousResearch · reported by VulDBLow 2.1
A flaw has been found in NousResearch hermes-agent 0.18.0. Affected by this issue is some unknown functionality of the file gateway/platforms/api_server.py of the component Session Chat Interface. This manipulation causes denial of service. The attack is possible to be carried out remotely. The exploit has been published and may be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- hermes-agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 31, 2026Improper neutralization of special elements used in an OS command ('OS command injection') vulnerability in Digitální a informační agentura (DIA) eObčanka-IdentCVE-2026-59111 · Other software · Ministry of the Interior (MVČR) · reported by a6d3dc9e-0591-4a13-bce7-0f5b31ff6158Critical 9.3
Improper neutralization of special elements used in an OS command ('OS command injection') vulnerability in Digitální a informační agentura (DIA) eObčanka-Identifikace on MacOS enables an attacker to register a custom URL scheme (czeeopauth://) for parameterized application execution. Prior to version 3.6.0, incoming URL parameters were passed to the compiled AppleScript wrapper using concatenation without sufficient sanitization.
- Product
- eObčanka-Identifikace
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 31, 2026In Eclipse Theia versions 1.73.0 up to but not including 1.75.0, the AI "Agent Mode" file-change tools (writeFileContent, suggestFileContent, and the replacemenCVE-2026-82217 · Other software · Eclipse Foundation · reported by emo@eclipse.orgHigh 8.8
In Eclipse Theia versions 1.73.0 up to but not including 1.75.0, the AI "Agent Mode" file-change tools (writeFileContent, suggestFileContent, and the replacement and state helpers) resolved a model-supplied file path without a workspace-containment check. A crafted relative path such as ../.bashrc, an absolute path, or a ~-expanded path could therefore write or delete files outside the workspace with the privileges of the Theia backend OS user. Because the path argument is influenced by model output, it can be steered through indirect prompt injection, and in Agent Mode writes are applied without a confirmation dialog. Writing to a host-executed file such as a shell startup file or ~/.ssh/authorized_keys can escalate to code execution on the backend.
- Product
- Eclipse Theia
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comgitlab.eclipse.org
Aug 30, 2026Keploy versions 3.1.0 through 3.6.25, fixed in 3.6.26, bind the agent control-plane HTTP server to all interfaces without authentication, exposing endpoints thaCVE-2026-82641 · Other software · Keploy · reported by VulnCheckHigh 8.8
Keploy versions 3.1.0 through 3.6.25, fixed in 3.6.26, bind the agent control-plane HTTP server to all interfaces without authentication, exposing endpoints that stream TLS session keys and traffic data. Attackers can access the /agent/pcap/keylog endpoint to retrieve NSS keylog lines and decrypt recorded TLS traffic, or invoke /agent/stop and /agent/storemocks to manipulate recording sessions.
- Product
- Keploy
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 30, 2026browser-use web-ui versions 2.0.0 through 3.0.0 fail to validate browser settings paths in run_agent_task, allowing attackers to create directories at arbitraryCVE-2026-82637 · Other software · browser-use · reported by VulnCheckMedium 6.9
browser-use web-ui versions 2.0.0 through 3.0.0 fail to validate browser settings paths in run_agent_task, allowing attackers to create directories at arbitrary locations by supplying absolute paths to save_recording_path, save_trace_path, save_agent_history_path, or save_download_path parameters. Attackers can exploit this via the unauthenticated Gradio interface to create directories anywhere the root-running container has write access.
- Product
- web-ui
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 29, 2026iFlytek astron-agent through 1.1.1 contains an authorization bypass vulnerability in the copyFlow endpoint that fails to validate workflow ownership.CVE-2026-82475 · Other software · iflytek · reported by VulnCheckHigh 8.6
iFlytek astron-agent through 1.1.1 contains an authorization bypass vulnerability in the copyFlow endpoint that fails to validate workflow ownership. Authenticated attackers can enumerate workflow identifiers and overwrite other tenants' workflows or copy private workflows to read their definitions.
- Product
- astron-agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026VoltAgent through 2.1.20 fails to validate conversation ownership in memory API handlers, allowing authenticated users to access other users' conversations.CVE-2026-82283 · Other software · VoltAgent · reported by VulnCheckHigh 8.6
VoltAgent through 2.1.20 fails to validate conversation ownership in memory API handlers, allowing authenticated users to access other users' conversations. Attackers can read, modify, and delete arbitrary conversations and messages by supplying caller-controlled identifiers to memory endpoints.
- Product
- voltagent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026Qwen-Agent through 0.0.34 contains a path traversal vulnerability in the document parser that fails to restrict file access to intended directories.CVE-2026-82275 · Other software · QwenLM · reported by VulnCheckHigh 8.7
Qwen-Agent through 0.0.34 contains a path traversal vulnerability in the document parser that fails to restrict file access to intended directories. Attackers can supply absolute file paths to the unauthenticated Gradio interface to read arbitrary files accessible by the server process.
- Product
- Qwen-Agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026Qwen-Agent through 0.0.34 contains a server-side request forgery vulnerability in the document parsing path that treats caller-supplied paths as URLs without scCVE-2026-82268 · Other software · QwenLM · reported by VulnCheckHigh 8.7
Qwen-Agent through 0.0.34 contains a server-side request forgery vulnerability in the document parsing path that treats caller-supplied paths as URLs without scheme restriction or host validation. Attackers can reach the unauthenticated Gradio interface to make the server issue HTTP requests to arbitrary internal addresses including metadata services and read retrieved content through parsed document output.
- Product
- Qwen-Agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026Hermes Agent 0.18.2 prior to 0.19.0 contains a supply chain vulnerability in its bundled MCP catalog that allows a remote attacker to execute arbitrary code by CVE-2026-82021 · Other software · NousResearch · reported by VulnCheckCritical 9
Hermes Agent 0.18.2 prior to 0.19.0 contains a supply chain vulnerability in its bundled MCP catalog that allows a remote attacker to execute arbitrary code by compromising a third-party upstream repository referenced via a mutable branch rather than a pinned commit SHA. An attacker who compromises the upstream repository can propagate malicious code to every host that installs the affected catalog entry, with no further action required by the operator.
- Product
- hermes-agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026Hermes Agent 0.16.0 prior to 0.17.0 contains an improper path restriction vulnerability that allows attackers who can influence ingested message content to overCVE-2026-82020 · Other software · NousResearch · reported by VulnCheckHigh 7.6
Hermes Agent 0.16.0 prior to 0.17.0 contains an improper path restriction vulnerability that allows attackers who can influence ingested message content to overwrite the credential store by bypassing sensitive-path guards that excluded the auth.json file. Attackers can craft malicious messages directing the agent's file-write tooling to overwrite the credential store without triggering any path-based protection, enabling credential tampering or unauthorized access.
- Product
- hermes-agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026Improper limitation of a pathname to a restricted directory in the aws:downloadContent plugin in amazon-ssm-agent before 3.3.4515.0 might allow an authenticatedCVE-2026-81849 · Other software · amazon · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5High 8.7
Improper limitation of a pathname to a restricted directory in the aws:downloadContent plugin in amazon-ssm-agent before 3.3.4515.0 might allow an authenticated remote user whose ssm:SendCommand permission is restricted to the AWS-DownloadContent document, to write arbitrary files outside the intended download directory with root privileges, via crafted object keys in the S3 source the document is directed to retrieve. This issue may lead to arbitrary code execution as root if specific sensitive files are overwritten. To remediate this issue, customers should upgrade amazon-ssm-agent to version 3.3.4515.0 or later.
- Product
- amazon-ssm-agent
- 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
Aug 28, 2026Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale.CVE-2026-54746 · Other software · hatchet-dev · reported by GitHubMedium 6.4
Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. From 0.40.0 until 0.91.1, the Dispatcher gRPC service does not verify that a request's worker ID belongs to the tenant identified by the bearer-token context in Dispatcher/UpsertWorkerLabels and Dispatcher/Unsubscribe. An authenticated owner of any tenant who guesses another tenant's worker UUID can overwrite that worker's affinity labels or disconnect the worker from the dispatcher. This can cause cross-tenant integrity impact and denial of service on multi-tenant Hatchet Cloud or shared self-hosted deployments. Single-tenant deployments are not practically affected because the attacker and target tenant are the same. This issue is fixed in version 0.91.1.
- Product
- hatchet
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026An OS command injection vulnerability in the killSessionSync function (lib/agent-runtime.ts) of 23blocks-OS ai-maestro v0.24.17 allows attackers to execute arbiCVE-2026-37751 · Other software · reported by MITRECritical 9.8
An OS command injection vulnerability in the killSessionSync function (lib/agent-runtime.ts) of 23blocks-OS ai-maestro v0.24.17 allows attackers to execute arbitrary commands via a crafted input.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026SiYuan versions before v3.8.1 contain a server-side request forgery vulnerability in the http_request and web_fetch agent tools that perform DNS resolution onlyCVE-2026-82234 · Other software · siyuan-note · reported by VulnCheckHigh 8.4
SiYuan versions before v3.8.1 contain a server-side request forgery vulnerability in the http_request and web_fetch agent tools that perform DNS resolution only at guard time without validating the connect-time resolution. Attackers can use DNS rebinding to answer the guard resolution with a public IP and the connect resolution with a private or metadata IP, bypassing the SSRF defense to access cloud instance metadata and internal services.
- Product
- siyuan
- 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
Aug 26, 2026A malicious actor with access to the network and high privileges could exploit an Improper Input Validation vulnerability found in UID Enterprise Agent to execuCVE-2026-77542 · Network & remote access · Ubiquiti Inc · reported by fe490ce8-0395-4072-90d8-2707e1bdf984Critical 9.1
A malicious actor with access to the network and high privileges could exploit an Improper Input Validation vulnerability found in UID Enterprise Agent to execute a Command Injection on the host device.
- Product
- UID Enterprise Agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026In Dradis Community Edition, the ProvidersController and AgentsController gate their admin_required before_action on `defined?(Dradis::Pro)`, a constant that isCVE-2026-79788 · Other software · dradis · reported by VulnCheckHigh 7.1
In Dradis Community Edition, the ProvidersController and AgentsController gate their admin_required before_action on `defined?(Dradis::Pro)`, a constant that is never defined in CE, so the authorization check is never applied. As a result, any authenticated (non-admin) user can create an AI provider pointing to an arbitrary HTTP/HTTPS address (including internal/link-local hosts such as http://169.254.169.254) and reassign the built-in Roslin agent to use it. When an AI interaction is triggered, the server issues a request to the attacker-supplied URL (server-side request forgery). For non-2xx responses, the target's response body is reflected verbatim to the attacker's browser via ActionCable/Turbo Stream error messages, making the SSRF readable.
- Product
- dradis-ce
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to executeCVE-2026-78379 · Other software · Amazon · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Critical 9.2
Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.
- 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.compypi.org
Aug 25, 2026QWED is open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production eCVE-2026-55585 · Other software · QWED-AI · reported by GitHubHigh 8.8
QWED is open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution. Prior to 5.1.2, the qwed package passes caller-controlled math expressions directly to SymPy parse_expr() without restricted global_dict and local_dict namespaces, allowing Python eval() to resolve builtins and execute arbitrary Python code in the API server process. In src/qwed_new/api/main.py, POST /verify/math is protected by get_current_tenant but accepts any valid tenant API key, reads the expression field, applies only a cosmetic re.sub(r'(\d)(()', r'\1*\2', expression) normalization, and passes the result to parse_expr(). In src/qwed_new/core/batch.py, POST /verify/batch sends math items through batch_service.create_job(), stores item.query verbatim, and _verify_item() passes VerificationType.MATH input to parse_expr() without sanitization. The default-enabled POST /auth/signup endpoint allows anyone to create a standard tenant account, POST /auth/api-keys issues an x-api-key, and either vulnerable path can then be used to read or write files, modify data, execute operating system commands, terminate the ser
- Product
- qwed-verification
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents.CVE-2026-55557 · Other software · That1Drifter · reported by GitHubHigh 8.6
browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents. Prior to 0.8.2, browser_download writes a fetched response body to join(save_dir, filename) without validating the caller-controlled save_dir, while browser_save_state and browser_load_state honor a caller-controlled path unchanged. A malicious MCP client, or an autonomous agent steered by indirect prompt injection on a visited page, can choose an arbitrary save_dir or state path and a URL whose response body becomes attacker-controlled file contents, allowing writes to any path the process can reach, including ~/.bashrc, autostart entries, or cron files, and potentially leading to host code execution. The force_fetch fallback also uses a raw fetch() that bypasses the BROWSE_MCP_ALLOWED_ORIGINS origin fence. This issue is fixed in version 0.8.2.
- Product
- browse-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55539 · Other software · MervinPraison · reported by GitHubHigh 8.6
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, the Jobs API create_app function mounts /api/v1/runs without authentication. Any reachable caller can submit jobs, read results, cancel runs, or delete jobs using operator credentials. The fix adds PRAISONAI_JOBS_API_KEY middleware for Authorization or X-API-Key. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55536 · Other software · MervinPraison · reported by GitHubCritical 9.1
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, Browser Server _handle_connection() checks Chrome extension origins with re.match() and the unanchored expression chrome-extension://[a-z0-9]{32}. Extra trailing characters pass before websocket.accept(), allowing start_session commands and unauthorized browser automation. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55533 · Other software · MervinPraison · reported by GitHubHigh 8.2
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, create_auth_middleware() allows requests when auth=api-key lacks PRAISONAI_API_KEY or JWT authentication lacks PRAISONAI_JWT_SECRET. An externally bound Recipe server can therefore accept unauthenticated POST /v1/recipes/run requests despite authentication being enabled. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55532 · Other software · MervinPraison · reported by GitHubHigh 7.6
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests without preflight and invoke tools/call without an API key, including file writes that persist agent instructions. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55541 · Other software · MervinPraison · reported by GitHubHigh 8.8
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, praisonai serve agents and praisonai serve unified parse --api-key but _create_agents_app() and _create_unified_app() do not install a credential check. Unauthenticated callers can reach POST /agents and POST /api/v1/agents/{id}/invoke. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55540 · Other software · MervinPraison · reported by GitHubHigh 7.1
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, is_path_within_directory() uses os.path.abspath() rather than os.path.realpath() for the workspace boundary. A symlink inside workspace can point outside and still pass the check, allowing read_file and other code tools to access files outside the configured workspace. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55538 · Other software · MervinPraison · reported by GitHubHigh 7.3
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, praisonai serve agents parses config["api_key"] but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. Missing or incorrect bearer and X-API-Key values still reach agent execution. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55537 · Other software · MervinPraison · reported by GitHubHigh 7.1
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, JobSubmitRequest.validate_webhook_url() accepts webhook_url when resolution raises socket.gaierror because the exception path uses except socket.gaierror: pass. JobExecutor._send_webhook() later performs a fresh lookup, allowing DNS changes to direct the request to an internal service. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55535 · Other software · MervinPraison · reported by GitHubMedium 6.8
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the Jobs API validate_webhook_url() path fails open on socket.gaierror and does not bind the validated address to the later request. An attacker webhook_url can later resolve to 127.0.0.1, 169.254.169.254, or another internal address. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55534 · Other software · MervinPraison · reported by GitHubHigh 8.6
PraisonAI is a multi-agent teams system. From praisonai 4.6.34 until 4.6.58, praisonai serve agents accepts --api-key but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. A network caller can invoke configured agents without credentials even when an API key was supplied. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55531 · Other software · MervinPraison · reported by GitHubMedium 6.5
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream mcp_post handler creates a new _sessions entry for every initialize request but does not call _cleanup_sessions or enforce a maximum. An unauthenticated caller can exhaust memory. The fix invokes cleanup and limits sessions through PRAISONAI_MCP_MAX_SESSIONS. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55530 · Other software · MervinPraison · reported by GitHubMedium 6.1
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, ast_grep_rewrite lacks the @require_approval decorator used by sibling mutation tools. With dry_run=False, an agent-controlled call can pass --update-all and a broad path to rewrite matching files without the expected authorization gate. This issue is fixed in version 1.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55529 · Other software · MervinPraison · reported by GitHubMedium 6.9
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream _validate_origin method accepts request_origin.startswith(allowed), so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit tools/call requests to the local MCP server and execute exposed tools. This issue is fixed in version 4.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55528 · Other software · MervinPraison · reported by GitHubHigh 8.2
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, AgentServer exposes ServerConfig.auth_token but AgentServer._create_app does not check it on any route. A remote caller can subscribe, publish, and perform other actions without a valid bearer token or X-Auth-Token even when authentication is configured. This issue is fixed in version 1.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55527 · Other software · MervinPraison · reported by GitHubHigh 7.1
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the FileMemory constructor joins unsanitized user_id into self.user_path. A caller supplying ../ or path separators can escape the memory directory and write JSON data to arbitrary process-writable locations. The fix sanitizes user_id before constructing self.user_path. This issue is fixed in version 1.6.58.
- Product
- PraisonAI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026PraisonAI is a multi-agent teams system.CVE-2026-55526 · Other software · MervinPraison · reported by GitHubHigh 8.5
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, spider_tools._host_is_blocked() does not resolve ordinary hostnames before scrape_page fetches them. A hostname such as 127.0.0.1.nip.io passes validation and resolves to loopback, permitting internal HTTP access. The fix uses socket.getaddrinfo and fails closed on DNS errors. This issue is fixed in version 1.6.58.
- Product
- PraisonAI
- 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.