About this skill
Walk the current diff (or the whole repo) against SECURITY.md's trust-boundary table and "Where I'd look" list, invariant by invariant, delegating the adversarial review to the hub-security-adversary agent. Use before merging anything that touches auth, transport, parsing, rendering, or path handling — or on request for a periodic sweep.
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.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: 931b32d23ee2f32fe0d96f80b7933e5862d8fd5b52b32239cdb481191bcd592c
About this listing
- Category
- Security
- Reported license
- GPL-3.0
- 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.