review-testing

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues or malicious behaviors were detected. The skill is limited to providing structured feedback on code quality.- [PROMPT_INJECTION]: No evidence of direct prompt injection, role-play jailbreaks, or instructions to bypass safety guidelines was found. The skill has a surface for indirect prompt injection via the analyzed source code, but this is mitigated by the lack of any executable or state-changing capabilities within the skill's logic.- [EXTERNAL_DOWNLOADS]: The README mentions an installation command using 'npx' to fetch the skill from the vendor's repository ('nesnilnehc/ai-cortex'). This is a standard distribution method for this author and does not involve unauthorized remote script execution.- [COMMAND_EXECUTION]: The skill explicitly restricts itself from executing code or running tests, ensuring it only performs cognitive analysis. No dangerous system commands or shell access patterns were observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 09:05 AM