Agentic / MCP
942 entries
Every Agentic / MCP entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
CVE-2026-46580: In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were auto
In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An...
CVE-2026-44688: In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its
In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacke...
CVE-2026-22551: In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP r
In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt inj...
Orphaned AI Agents: How to Find Hidden Access Risks Inside Your Network
If an autonomous AI agent interacts with your company's core intellectual property today, can your security team instantly name the person who authorized it? For most enterprises, the answer is a sim...
PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation
## Summary The `multiedit` tool in `src/praisonai/praisonai/tools/multiedit.py` allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected...
npm PraisonAI MCPServer exposes unauthenticated HTTP tools/call
## Summary The published npm package `praisonai` exports a TypeScript `MCPServer` that can expose tools, resources, and prompts over an HTTP JSON-RPC transport with: ```ts await server.start({ port:...
PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool
## Summary The `codeMode` tool in `src/praisonai-ts/src/tools/builtins/code-mode.ts` uses `new Function()` with a `with(sandbox)` pattern to execute LLM-generated code. The blocklist-based "sandbox"...
npm PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation
## Summary The published npm package `praisonai` exports an `MCPSecurity` helper described in source as: ```text MCP Security - Authentication, authorization, and rate limiting Provides security pol...
PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters
## Summary The email search tool in `src/praisonai-agents/praisonaiagents/tools/email_tools.py` constructs IMAP SEARCH commands by interpolating LLM-controlled parameters (from_addr, subject, query)...
PraisonAI: Missing Authentication for Critical Function and Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in praisonai
# Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands ## Summary PraisonAI v4.6.48 exposes the PraisonAIUI MCP client management API through the default UI host...
praisonai: recipe serve auth middleware silently disables itself when no secret is set
# praisonai: `recipe serve` authentication middleware silently disables itself when no secret is set **Researcher:** Kai Aizen — SnailSploit (@SnailSploit), Adversarial & Offensive Security Research...
PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools
# PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools ## Summary `praisonaiagents.mcp.ToolsMCPServer.run_sse()` builds a Starlette MCP HTTP+SSE se...
Docker MCP Gateway: Argument injection via OCI image label YAML
## Summary A maliciously crafted OCI image label can inject arbitrary arguments into the `docker run` command line constructed by the MCP Gateway. An attacker who controls an image that the victim re...
Is it agentic enough? Benchmarking open models on your own tooling
CVE-2026-48989: Windows-MCP is an open-source project that integrates AI agents with Windows. In versions prior to 0.7.5, certain HTTP m
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 wildcar...
CVE-2026-48814: Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows un
Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows unauthenticated cross-origin MCP tool invocation due to an empty default secret. T...
CVE-2026-20265: In Splunk AI Toolkit versions below 5.7.4, a low-privileged user that does not hold the "admin" or "power" Splunk roles
In Splunk AI Toolkit versions below 5.7.4, a low-privileged user that does not hold the "admin" or "power" Splunk roles could cause the Splunk AI Toolkit to make outbound requests over HTTP to a serve...
OpenClaw: MCP Streamable HTTP redirects could forward configured custom headers to another origin
### Summary OpenClaw supports remote MCP Streamable HTTP servers with operator-configured custom headers. In affected releases, those headers could be forwarded when the MCP endpoint responded with a...
1Password Acquires Apono in Reported $250M-$300M Deal
Apono specializes in just-in-time access governance technology for humans, machines, and AI agents. The post 1Password Acquires Apono in Reported $250M-$300M Deal appeared first on SecurityWeek.
Tenet Security Emerges From Stealth With $6 Million Seed Funding
Tenet aims to detect and stop dangerous AI agentic behavior in real time. The post Tenet Security Emerges From Stealth With $6 Million Seed Funding appeared first on SecurityWeek.
Duplicate Advisory: MCP Streamable HTTP redirects could forward configured custom headers to another origin
## Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-rjxq-qqhf-8hwh. This link is maintained to preserve external references. ## Original Description OpenClaw befo...
CVE-2026-53840: OpenClaw before 2026.5.12 contains an information disclosure vulnerability in streamable-http MCP servers that forwards
OpenClaw before 2026.5.12 contains an information disclosure vulnerability in streamable-http MCP servers that forwards operator-configured custom headers during cross-origin redirects. Attackers cont...
Magnitude Emerges From Stealth Mode With $10 Million in Funding
The company is enhancing third-party risk management (TPRM) through autonomous AI agents. The post Magnitude Emerges From Stealth Mode With $10 Million in Funding appeared first on SecurityWeek.
NewCore Emerges From Stealth Mode With $66 Million in Funding
The startup has built a security-first identity platform to protect humans, machines, and AI agents. The post NewCore Emerges From Stealth Mode With $66 Million in Funding appeared first on SecurityWe...