code-review

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the coderabbit command-line utility and a local Python parsing script (parse_plain_review.py) to process code review results. This is the primary intended function of the skill.
  • [SAFE]: Explicit safety instructions are included to treat all repository content and CLI output as untrusted input, preventing the agent from autonomously executing potentially malicious code found in reviews.
  • [SAFE]: The skill mandates the redaction of secrets and credentials in all shared logs and summaries to prevent accidental data exposure.
  • [SAFE]: Includes validation steps and non-goals to ensure the agent does not attempt unauthorized actions like modifying billing plans or bypassing authentication checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 01:12 PM
Security Audit — agent-trust-hub — code-review