Latest
●Mem0 memory keys can be forged to read other tenants' chats●vLLM's wildcard CORS default let any website query local servers●Rust zip crate flaw lets archives hide a second filename●Microsoft says agents in Microsoft 365 grew 15-fold in a year●Attacker Poses as AI Crawlers to Hunt for Exposed Credentials●Functype MCP server flaw let tool calls run arbitrary code●Token Security says blast radius matters more than patch speed●OpenAI agent validated 14 leaked Hugging Face tokens
Thursday, 29 October 2026
0 agent hacks today▼ 6 vs yesterday (6)
The Agentic TimesPowered byVortal

Incident database

SSRF in JoeCastrom mcp-chat-studio LLM Models API (CVE-2026-7147)

A server-side request forgery vulnerability (CVE-2026-7147) affects JoeCastrom mcp-chat-studio up to version 1.5.0, where manipulation of the req.query.base_url argument in server/routes/llm.js of the LLM Models API allows remote exploitation. The exploit is public and the project has not responded to the issue report.

Disclosed 27 April 2026 · Record updated 1 October 2026

Impact

Remote attackers can trigger server-side request forgery via a user-controlled base_url parameter; a public exploit is available and the maintainer has not responded.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-7147