Skills
Navigate
skills/kevmoo/kevmoo_skills/pr-review/Gen Agent Trust Hub

pr-review

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub PRs and Issues via gh pr diff and gh issue view in SKILL.md. This content could contain malicious instructions designed to subvert the agent's logic. Ingestion points: GitHub PR diffs and Issue bodies. Boundary markers: None identified. Capability inventory: The skill can execute git push, git stage, and a local script kscripts pr-check. Sanitization: No validation or sanitization of external content is performed.
  • [COMMAND_EXECUTION]: The skill executes dart run api_summary@^1.1.0 and a local script kscripts pr-check as part of the review workflow.
  • [EXTERNAL_DOWNLOADS]: The skill triggers the download of the api_summary package from the public Dart registry.
  • [DATA_EXFILTRATION]: The skill reads from ~/.agents/CODING_STANDARDS.md. Accessing files in the home directory is a risk for sensitive data exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 11:35 PM