github-ops

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls and parses public, user-generated GitHub content (e.g., gh api repos/{owner}/{repo}/pulls, gh pr view --json, gh issue view, gh workflow view --yaml and downloading run logs) as shown in SKILL.md and references/api_reference.md, and those fetched PRs, issues, comments, workflow YAML and logs are then used in automation examples (auto-merge, review/approve, trigger workflows), so untrusted third-party content can influence agent actions.