review-pr

Warn

Audited by Snyk on Feb 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and parse pull request diffs and repository files (via git/gh), including PR descriptions and repository files like README.md/CLAUDE.md/constitution.md on GitHub, which are user-generated/untrusted content the agent will read.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 13, 2026, 07:45 AM