readme-doctor
Warn
Audited by Snyk on Feb 20, 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). This skill's SKILL.md explicitly instructs fetching and analyzing public GitHub README files (e.g., Mode 2 "Analyze https://github.com/…" and Mode 3 GitHub Pattern Analysis using
gh api /repos/<owner>/<repo>/readme), which are untrusted, user-generated third‑party content that the agent reads and uses to drive prescriptions and actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). This skill explicitly fetches remote README content at runtime (e.g., "https://github.com/vercel/next.js/blob/canary/README.md" via the shown gh/api or direct fetch) and injects that content into its analysis/prescription flow, meaning external content can directly influence the agent's prompts and outputs.
Audit Metadata