Skill profile
security-threat-model
Produces a repository-grounded threat model — trust boundaries, assets, attacker capabilities, abuse paths, mitigations — written to a markdown file. Roughly half its description is negative triggers.
What it actually does
- Produces a repository-grounded threat model — trust boundaries, assets, attacker capabilities, abuse paths, mitigations — written to a Markdown file.
When to use it — and when not to
Use it when
- You want a structured threat model grounded in the actual repository, not a generic security checklist.
Not for
- General architecture summaries, code review, or non-security design work — roughly half its own description is negative triggers spelling this out.
Agent compatibility
- Codex
Confirmed means the skill’s own source or vendor states it works with that agent. Portable means it only reaches that agent through the shared SKILL.md format and a directory convention — real, but a weaker claim. An agent with no entry here isn’t known to be unsupported; it simply isn’t documented either way, so nothing is claimed. Full model on Agent Skills Compatibility.
Requirements and operational surface
What it actually does at runtime
- Reads the repository
- Writes a Markdown file with the resulting threat model
Workflow fit
Codebase mapping → threat modeling → mitigation planning → implementation.
Related skills
- audit-context-buildingDifferent agents, same phase of the job — audit-context-building maps a codebase before review; this produces the review's output.
Evidence and provenance
Maintained by OpenAI (official). Primary source: openai/skills (curated), last checked against this page’s claims on . This page summarizes and analyzes that source — it isn’t a copy of its SKILL.md or README, and installation happens at the source, not here.
Also covered in The Best Codex Skills, part of the Codex guide.