Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLIAbout this skill
ASK (Agent Security Framework) threat analyst — ASK 2026.04. Use this skill whenever the user wants to: analyze threats to AI agent systems; assess XPIA (cross-prompt injection attack) kill chain posture; evaluate attack surfaces; review defensive architecture against specific threat categories; understand traditional vs novel vs hybrid threats to agents; analyze MCP security risks; assess identity/memory poisoning risks; evaluate behavioral drift detection; review multi-agent cascade failure risks; or understand ASK framework limitations and known gaps. Trigger on any mention of agent threat model, XPIA analysis, prompt injection defense, agent attack surface, MCP security, identity poisoning, behavioral drift, cascade failures, agent threat assessment, kill chain analysis, or ASK limitations.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
1 potential finding · Scanned 11/4/2026 · Scanner 0.2.1
- high: instruction override — SKILL.md, line 166
Content SHA-256: efbbab492b8544cd325fb50bebd1a059da06c7856e67a02b694d70e2bc91a350
About this listing
- Category
- Security
- Reported license
- Not specified
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.