github-repo-management
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill fetches and summarizes repository metadata and pull requests from GitHub via GitHub MCP (repo descriptions, PR titles/bodies, branches), which are user-generated, public third-party content that the agent is expected to read and could carry indirect prompt-injection.
Audit Metadata