About this skill
Security-review methodology for the security-reviewer-agent — surfaces fuzzy security risks the deterministic lint cannot see (prompt-injection openings, scope-bypass patterns, missing actor envelope threading, over-broad MCPToolBox permissions, suspicious external host references, missing approval gates on risky writes, credential-shaped variables in prompts, leaked PII in description/system fields).
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 43
Content SHA-256: 5fc84eabe57a7e4a08acb38a349dfd153bb7396c7fffec159b12bcc78a8b30a5
About this listing
- Category
- Security
- Reported license
- Apache-2.0
- 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.