skill-discovery
Warn
Audited by Snyk on Mar 1, 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 calls the public GitHub API (githubRequest in discover.js and evaluate.js, e.g., /search/repositories and /repos/.../readme and /topics) and directly reads untrusted repository metadata, README and topics to score, recommend, and auto-generate manifests—so attacker-controlled, user-generated content from GitHub can materially influence recommendations and subsequent integration actions.
Audit Metadata