skills/cmds-cc/skills/wmill-review/Gen Agent Trust Hub

wmill-review

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from repository files and diffs.
  • Ingestion points: The agent reads CLAUDE.md files and pull request diffs using gh pr diff or git diff (Step 2 and 3).
  • Boundary markers: There are no explicit delimiters or instructions telling the agent to disregard instructions found within the data it is analyzing.
  • Capability inventory: The skill can perform write operations on GitHub, such as posting reviews and comments via gh pr review and the GitHub API (Step 7).
  • Sanitization: No content validation or sanitization is performed on the data ingested from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 07:02 PM