skills/shipshitdev/library/review-pr/Gen Agent Trust Hub

review-pr

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for manual or automated code review and does not perform any automated actions, network requests, or command executions.
  • [NO_CODE]: No executable scripts or binary files are included in the skill; it consists entirely of markdown documentation and configuration metadata.
  • [PROMPT_INJECTION]: The skill is intended to review pull request data, which constitutes processing untrusted external input.
  • Ingestion points: Pull request content (code and diffs) enters the agent context.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined in SKILL.md.
  • Capability inventory: The skill does not define or use any tools, scripts, or subprocesses.
  • Sanitization: No sanitization or validation of the processed code is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 07:31 AM