repo-summary
Warn
Audited by Snyk on Mar 8, 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 explicitly ingests and analyzes data from arbitrary GitHub repositories (via the /repo-summary [owner/repo] input and the "Run repo-activity to gather GitHub metrics" implementation), meaning it reads untrusted, user-generated content like commits, issues, and PRs that directly influence the agent's analysis and decisions, enabling indirect prompt injection.
Audit Metadata