skills/metamask/skills/pr-codeowners/Gen Agent Trust Hub

pr-codeowners

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard git commands to identify changed files and reads the project's CODEOWNERS file to determine ownership. This is a common development workflow automation with no evidence of malicious intent or behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes the content of the .github/CODEOWNERS file, which is an external data source within the repository. While this represents an attack surface for indirect prompt injection if a malicious actor modifies the file, the skill's specific instructions to match patterns and collect team names for a lookup table limit the risk.
  • Ingestion points: .github/CODEOWNERS file.
  • Boundary markers: None.
  • Capability inventory: Shell command execution (git diff) and file reading.
  • Sanitization: None mentioned, though extraction is limited to specific team patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 07:59 PM
Security Audit — agent-trust-hub — pr-codeowners