Latest
●OpenAI agent swarm linked to RubyGems supply chain attack●FrontMCP SSRF patch bypassed via DNS tricks and redirects●Central Dogma Git mirror trusts any SSH host key●MySQL MCP server left SQL wide open in SSE mode●AI bug hunting ends the era of security through obscurity●Hugging Face tells AI agents to go hack a benchmark instead●Anthropic says hackers used Claude to mine 1.8M Android apps●Anthropic says Claude was abused to automate attacks and weapons work
Sunday, 13 September 2026
8 agent hacks today▲ 7 vs yesterday (1)
The Agentic TimesPowered byVortal

Incident database

AnythingLLM agent filesystem skills allow command execution and path escape

Two vulnerabilities in AnythingLLM prior to 1.13.0 let an attacker chatting with an agent abuse the filesystem skills: an LLM-controlled ripgrep pattern (--pre=/bin/sh) enabled arbitrary command execution inside the server container, and the copy tool followed nested symlinks to copy files from outside the allowed filesystem root. Both were fixed in version 1.13.0.

Disclosed 28 May 2026 · Record updated 13 September 2026

Impact

Attackers able to chat with an agent on a deployment with the filesystem plugin enabled (default in the official Docker image) could run arbitrary commands in the AnythingLLM server container and copy files from outside the permitted filesystem root.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-45403
  2. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-48116