Assess Agent & MCP security Defense not yet reviewed
agent-threat-rules
ATR (Agent Threat Rules) is an open, YAML-based detection rule format and reference engine (TypeScript, with a Python wrapper) for threats against AI agents, covering prompt injection, tool poisoning, and credential exfiltration. It is aimed at teams building or operating agent runtimes, MCP integrations, and CI/SIEM pipelines.
Promising or important to understand; evaluate, don't depend on it yet.
Facts
- Repository
- Agent-Threat-Rule/agent-threat-rules
- Homepage
- github.com
- Listed via
- GitHub topic
- First seen
- 2026-11-08
- License
- MIT
- Stars
- 426
- Last commit
- 2026-11-08
- Checked
- 2026-11-08
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.