snap

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and parses repository files and metadata from external GitHub repos (e.g., reading eng/Versions.props and eng/config/PublishData.json via gh/darc calls and git show) and uses those values to build merge commits, PRs, darc channel changes, and execution decisions, so untrusted third-party content can directly influence tool actions.