Skip to content

Agent Threat Rules

Named by 2 kept items in this workspace.

Search every workspace for Agent Threat Rules. It matches the name as written, so it can find other things that share it.

The items that name it 2

  • awesome-ai-security-tools
    repo2026-07-11It is written here as agent-threat-rules (ATR).

    Open, versioned, machine-readable detection rules for AI-agent threats (prompt injection, tool poisoning, MCP attacks, skill compromise); 768 rules across 10 categories

  • Agent Threat Rules (ATR) — Sigma/YARA-style open detection format for AI agent threats
    otherIt is written here as Agent Threat Rules (ATR).

    Open, vendor-neutral detection rule format for AI agent security threats (prompt-injection, tool-poisoning, credential-exfiltration, unauthenticated agent-execution); YAML-based rules identified by ATR-YYYY-NNNNN scheme, evaluated by conforming engines; reference TypeScript engine and Python wrapper

All technologies in this workspace.