27445 matches found
FLAWED
F ix L ike A rtifacts w ith E mbedded D efects A research harness for measuring how well AI agents patch vulnerabilities. Quickstart Β· Datasets Β· Documentation Β· Security model Β· Contributing FLAWED checks out an open-source project at a known-vulnerable commit, hands an AI agent a description of...
CVE-2026-55376
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to 0.0.40, an authenticated user who can create or edit a workflow with an Agent custom Python tool can bypass the blacklist-based sandbox in backend/app/services/pythontoolexecutor.py becau...
T-MAP
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search T-MAP is a trajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers. It iteratively generates and mutates adversarial prompts guided by execution trajectories, mapping the agent's vulnerabili...
CVE-2026-74047
Wazuh from 4.0.0 before 4.14.8 contains an information disclosure vulnerability that allows low-privileged users with agent:read to retrieve the plaintext authd.pass enrollment password via the unmasked agent configuration endpoint. Attackers holding the default readonly role can request the auth...
CVE-2026-74047 Wazuh 4.0.0 before 4.14.8 authd.pass Disclosure via Agent 000 Config Endpoint
Wazuh from 4.0.0 before 4.14.8 contains an information disclosure vulnerability that allows low-privileged users with agent:read to retrieve the plaintext authd.pass enrollment password via the unmasked agent configuration endpoint. Attackers holding the default readonly role can request the auth...
CVE-2026-74047 Wazuh 4.0.0 before 4.14.8 authd.pass Disclosure via Agent 000 Config Endpoint
Wazuh from 4.0.0 before 4.14.8 contains an information disclosure vulnerability that allows low-privileged users with agent:read to retrieve the plaintext authd.pass enrollment password via the unmasked agent configuration endpoint. Attackers holding the default readonly role can request the auth...
CVE-2026-74047
Wazuh versions 4.0.0 before 4.14.8 are susceptible to an information disclosure vulnerability. Low-privileged users with agent:read permissions (specifically the default readonly role) can access the unmasked agent configuration endpoint. By requesting the auth component configuration for pseudo-...
CVE-2026-109403
A vulnerability was determined in conductor-oss conductor up to 3.32.5. Affected by this vulnerability is the function A2AService.getAgentCard of the file ai/src/main/java/org/conductoross/conductor/ai/a2a/A2AService.java of the component Agent Card Fetching. Executing a manipulation of the...
CVE-2026-109404
A server-side request forgery (SSRF) vulnerability exists in conductor-oss conductor versions up to 3.33.0-rc10 . The flaw originates from an unspecified functionality within the AgentController.java file, specifically located in the Agentspan Agent Runtime component. This vulnerability allows fo...
CVE-2026-109403
The conductor-oss conductor software (up to version 3.32.5 ) is vulnerable to Server-Side Request Forgery (SSRF) in the Agent Card Fetching component. The flaw exists within the A2AService.getAgentCard function located in the file ai/src/main/java/org/conductoross/conductor/ai/a2a/A2AService.java...
CVE-2026-109403 conductor-oss conductor Agent Card Fetching A2AService.java A2AService.getAgentCard server-side request forgery
A vulnerability was determined in conductor-oss conductor up to 3.32.5. Affected by this vulnerability is the function A2AService.getAgentCard of the file ai/src/main/java/org/conductoross/conductor/ai/a2a/A2AService.java of the component Agent Card Fetching. Executing a manipulation of the...
DeepTrap
DeepTrap English | δΈζ Open-world security evaluation for OpenClaw agents under adversarial execution contexts. DeepTrap is a security benchmark for evaluating whether OpenClaw agents can complete benign user tasks while resisting malicious execution-context pressure: poisoned workspace files,...
CVE-2026-96893
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user to inject specially crafted content into AI agent instructions, potentially causing...
CVE-2026-105458
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user holding a specific granular permission to obtain a GitLab Duo Agent Platform token that...
CVE-2026-105458
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user holding a specific granular permission to obtain a GitLab Duo Agent Platform token that...
EUVD-2026-98213
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user to inject specially crafted content into AI agent instructions, potentially causing...
CVE-2026-96893 Improper Neutralization of Input Used for LLM Prompting in GitLab
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user to inject specially crafted content into AI agent instructions, potentially causing...
CVE-2026-96893
GitLab EE is vulnerable to Improper Neutralization of Input Used for LLM Prompting (CWE-1427) in the GitLab Duo Agent Platform . This flaw allows an authenticated user to inject specially crafted content into AI agent instructions due to improper neutralization of special elements during AI conve...
CVE-2026-105458 Reliance on Untrusted Inputs in a Security Decision in GitLab
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user holding a specific granular permission to obtain a GitLab Duo Agent Platform token that...
EUVD-2026-98207
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user holding a specific granular permission to obtain a GitLab Duo Agent Platform token that...