CVE-2026-53766

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.resolvefilePath textually falls under one of the configured root paths. path.resolve...

DRUPAL-CONTRIB-2026-057

This module provides the entity type and runtime for Drupal AI Agents, enabling agents to use tools. Under certain circumstances, the agent inherits deterministic parameters when invoking the same tool in one request, which can lead to information disclosure...

DRUPAL-CONTRIB-2026-056

This module provides the entity type and runtime for Drupal AI Agents, enabling agents to use tools. The module does not sufficiently check the required permissions when a tool loads content entities. This vulnerability is mitigated by the fact that an agent must be configured to use the affected...

Jenkins Git client Plugin has an OS command injection vulnerability on agents

Jenkins Git client Plugin 6.6.0 and earlier does not correctly escape the workspace directory name when it is embedded into the SSH wrapper script generated by the "Manually provided keys" Git Host Key Verification strategy on Unix agents. This allows attackers able to control the name of a build...

GHSA-WP5X-HRRW-6R4G Jenkins Git client Plugin has an OS command injection vulnerability on agents

Jenkins Git client Plugin 6.6.0 and earlier does not correctly escape the workspace directory name when it is embedded into the SSH wrapper script generated by the "Manually provided keys" Git Host Key Verification strategy on Unix agents. This allows attackers able to control the name of a build...

AI Agents - Moderately critical - Information disclosure, Access bypass - SA-CONTRIB-2026-057

This module provides the entity type and runtime for Drupal AI Agents, enabling agents to use tools. Under certain circumstances, the agent inherits deterministic parameters when invoking the same tool in one request, which can lead to information disclosure...

PT-2026-52106

Name of the Vulnerable Software and Affected Versions chrome-devtools-mcp versions 0.24.0 through 1.0.9 Description A workspace-boundary bypass exists because the McpContext.validatePath function fails to canonicalize symbolic links when checking if a path falls under configured root paths. This...

PT-2026-52170

Name of the Vulnerable Software and Affected Versions Drupal AI Agents versions 0.0.0 through 1.1.4 Drupal AI Agents versions 1.2.0 through 1.2.5 Drupal AI Agents versions 1.3.0 through 1.3.1 Description An incorrect authorization issue allows forceful browsing. Under certain conditions, the agen...

PT-2026-52169

Name of the Vulnerable Software and Affected Versions Drupal AI Agents versions 0.0.0 through 1.1.4 Drupal AI Agents versions 1.2.0 through 1.2.5 Drupal AI Agents versions 1.3.0 through 1.3.1 Description Missing authorization allows forceful browsing within the module that provides the entity typ...

AI Agents - Less critical - Access bypass - SA-CONTRIB-2026-056

This module provides the entity type and runtime for Drupal AI Agents, enabling agents to use tools. The module does not sufficiently check the required permissions when a tool loads content entities. This vulnerability is mitigated by the fact that an agent must be configured to use the affected...

Oracle Linux 9 : fence-agents (ELSA-2026-13672)

The remote Oracle Linux 9 host has packages installed that are affected by multiple vulnerabilities as referenced in the ELSA-2026-13672 advisory. - bundled cryptography: replace with dependency to fix CVE-2026-26007 Tenable has extracted the preceding description block directly from the Oracle...

darknet-mcp-server

English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Fr...

CVE-2026-56693 NanoClaw < 2.1.17 - Privilege Escalation via Unauthorized create_agent System Action

NanoClaw before 2.1.17 contains a privilege escalation vulnerability in the createagent delivery-action handler that performs privileged central-database writes without host-side authorization checks. Confined agent containers can invoke createagent to create arbitrary agent groups, container...

CVE-2026-56693

NanoClaw prior to version 2.1.17 contains a privilege-escalation flaw in the create_agent delivery-action handler. It performs privileged central-database writes without host-side authorization checks, enabling confined agent containers to invoke create_agent to create arbitrary agent groups, con...

CVE-2026-56693 NanoClaw < 2.1.17 - Privilege Escalation via Unauthorized create_agent System Action

NanoClaw before 2.1.17 contains a privilege escalation vulnerability in the createagent delivery-action handler that performs privileged central-database writes without host-side authorization checks. Confined agent containers can invoke createagent to create arbitrary agent groups, container...

CVE-2026-56692 NanoClaw < 2.1.17 - Arbitrary File Read via Symlink Following in forwardAttachedFiles

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...

CVE-2026-56692

Vulnerability summary (CVE-2026-56692): NanoClaw prior to 2.1.17 contains a symlink-following flaw in forwardAttachedFiles that can exfiltrate host-readable files. The host validates attachments with isSafeAttachmentName, then copies via fs.copyFileSync, which follows symlinks without containment...

CVE-2026-56692

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...

PT-2026-51530

Name of the Vulnerable Software and Affected Versions NanoClaw versions prior to 2.1.17 Description An issue exists in the forwardAttachedFiles function where the host validates attachment filenames using only isSafeAttachmentName before performing a copy operation with fs.copyFileSync. Because...

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents

AI security agents increasingly rely on Retrieval-Augmented Generation RAG to use external security knowledge for vulnerability analysis and exploit reasoning. This creates a new risk: poisoned write-ups can be operationalized into incorrect exploit behavior. Yet, prior work on RAG poisoning has...