git-investigate

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md "Why was it changed? commit message + PR" and references/commands.md showing commands like git log, git show and gh pr view 123) clearly requires ingesting commit messages, PR text, and repository file contents (user-generated/untrusted third-party content) and using that data to drive investigation decisions, which could allow indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 06:41 AM