github-project-management

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and analyzes user-generated GitHub content (issue bodies, comments, labels and project items) via commands like "gh issue view ... --json body,comments", "gh issue list --json ...", and "npx ruv-swarm github triage --analyze-content" (e.g., stale-issue analysis and issue-decomposition), which exposes the agent to untrusted third-party content that could carry indirect prompt injections.