Agentic / MCP
435 entries
Every Agentic / MCP entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
Microsoft Warns Poisoned MCP Tool Descriptions Can Make AI Agents Leak Data
New Microsoft research shows how attackers can hijack AI agents that act on a user's behalf, using nothing more than a poisoned tool description to make the agent quietly hand over company data to an...
The AI Token Costs That Can Break Cybersecurity
As cybersecurity platforms embrace agentic AI, organizations must balance detection performance against the escalating costs of token consumption, deployment architecture, and AI credits. The post The...
CVE-2026-13437: Insertion of sensitive information into sent data in the AI Agent job API in Devolutions PowerShell Universal 2026.2.0 a
Insertion of sensitive information into sent data in the AI Agent job API in Devolutions PowerShell Universal 2026.2.0 allows an authenticated user with AI Agent read access to obtain reusable, potent...
CVE-2026-55607: Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of w
Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, e...
CVE-2026-46406: Claude Code is an agentic coding tool. From 2.1.59 until 2.1.128, the Claude Code /copy command wrote responses to a ha
Claude Code is an agentic coding tool. From 2.1.59 until 2.1.128, the Claude Code /copy command wrote responses to a hardcoded, predictable path (/tmp/claude/response.md) without UID isolation, rando...
Straiker Raises $64 Million for AI Security Platform
The startup’s platform can identify AI agents and provide visibility into their access, behavior, and risks. The post Straiker Raises $64 Million for AI Security Platform appeared first on SecurityWee...
Agentic AI Has an Identity Problem and Attackers Know It
AI agents can access data, trigger workflows, and take action across enterprise systems. Token Security explains why governing these privileged identities is becoming essential for enterprise security...
Clean GitHub repo tricks AI coding agents into running malware
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious payload that remains invisible to security scanners, AI agents, and human revie...
Streamable HTTP mode exposes LINE Desktop read/send tools without MCP authentication
# Streamable HTTP mode exposes LINE Desktop read/send tools without MCP authentication ## Summary `line-desktop-mcp` supports a `--http-mode` Streamable HTTP transport for use with clients such as n...
@cardano402/mcp-server missing spending limits, LAN-exposed HTTP transport, and SSRF via catalog.server.url
## Summary `@cardano402/mcp-server` versions `
mcp-pinot: Unauthenticated tool invocation via default oauth_enabled=False + host 0.0.0.0 bind
## Resolution Fixed in [v3.1.0](https://github.com/startreedata/mcp-pinot/releases/tag/v3.1.0), released 2026-05-25. The fix was merged in [PR #95](https://github.com/startreedata/mcp-pinot/pull/95)...
CVE-2026-48529: GitHub MCP Server is GitHub's official MCP Server. From 0.22.0 until 1.1.2, when running in HTTP mode with --lockdown-mo
GitHub MCP Server is GitHub's official MCP Server. From 0.22.0 until 1.1.2, when running in HTTP mode with --lockdown-mode enabled, the RepoAccessCache is implemented as a process-global singleton ini...
CVE-2026-4339: Mattermost versions 10.11.x <= 10.11.18, 11.6.x <= 11.6.3, 11.5.x <= 11.5.6 fail to validate attachment URLs against int
Mattermost versions 10.11.x
Amazon Q Developer Flaw Could Let Malicious Repos Run Code via MCP Configs
A high-severity flaw in Amazon Q Developer let a malicious repository run commands and steal a developer's cloud credentials. The path was short: a developer opens the repo, trusts the workspace, and...
Guardian Agents: The Next Layer of Identity Governance
AI agents are moving through enterprise environments, inheriting permissions, traversing systems, and executing decisions at machine speed with minimal oversight. The identity infrastructure built to...
New Enterprise-Ready MCP Specification Brings New Security Challenges
A major overhaul of the Model Context Protocol shifts critical security responsibilities from the protocol itself to developers and platform operators. The post New Enterprise-Ready MCP Specification...
CVE-2025-71336: Flowise before 3.0.6 (affected versions 2.2.7-patch.1 and earlier) contains an unsandboxed remote code execution vulnera
Flowise before 3.0.6 (affected versions 2.2.7-patch.1 and earlier) contains an unsandboxed remote code execution vulnerability in the Custom MCP feature, which is designed to execute OS commands such...
GitHub MCP Server: Lockdown mode singleton in HTTP server causes cross-user GraphQL client confusion
### Summary When running in HTTP mode with --lockdown-mode enabled, the RepoAccessCache is implemented as a process-global singleton initialized with the first authenticated user's GraphQL client. Al...
CVE-2026-55413: ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI
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 ti...
CVE-2026-55412: ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI
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 compon...
CVE-2026-55411: ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI
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-source...
CVE-2026-54030: LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implem
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Reso...
CVE-2026-55583: Twenty is an open-source CRM (customer relationship management) platform. Prior to 2.9.0, Twenty was vulnerable to a cro
Twenty is an open-source CRM (customer relationship management) platform. Prior to 2.9.0, Twenty was vulnerable to a cross-workspace insecure direct object reference (IDOR) in the AI agent monitor's A...
CVE-2026-54699: Warp is an agentic development environment. From 0.2024.03.12.08.02.stable_01 until 0.2026.05.06.15.42.stable_01, Warp c
Warp is an agentic development environment. From 0.2024.03.12.08.02.stable_01 until 0.2026.05.06.15.42.stable_01, Warp contains an OS command injection vulnerability in the WSL URL-opening fallback. W...