review-threat-model
Third stage of a guided AI security review. Produces the threat model for the subject type in review.json (model, agent in a harness, app, decision model, voice model, image model, agent feature) with OWASP LLM Top 10 2025, OWASP Agentic Top 10 and MITRE ATLAS ids where verified, and a test plan that sorts every threat into: covered by a catalogued benchmark (skill, benchmark, depth), needs a custom probe, design review only, or uncovered. Use after review-scope and before running any measurement skill. Names what to measure; prescribes no controls and sets no acceptance criteria.
- License
- MIT
- Compatibility
- Requires python>=3.10 (standard library only). No network, no API keys.
Pinned to revision 3fb15e11d58f, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/review-threat-model/SKILL.md
- skills/review-threat-model/catalog.json
- skills/review-threat-model/examples/review.example.json
- skills/review-threat-model/lib/evalkit.py
- skills/review-threat-model/references/agent-in-harness.md
- skills/review-threat-model/references/app.md
- skills/review-threat-model/references/decision-model.md
- skills/review-threat-model/references/feature.md
- skills/review-threat-model/references/framework-ids.md
- skills/review-threat-model/references/frameworks.json
- skills/review-threat-model/references/image-model.md
- skills/review-threat-model/references/model.md
- skills/review-threat-model/references/templates.json
- skills/review-threat-model/references/threats.json
- skills/review-threat-model/references/voice-model.md
- skills/review-threat-model/scripts/plan.py
- skills/review-threat-model/scripts/render_templates.py
- skills/review-threat-model/tests/test_plan.py
Every link opens the file at its source, pinned to the revision this page describes.