github-repo-candidate-quality-gate

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public, user-generated GitHub search results (calls out "Use gh search repos" and "Collect raw hits" in SKILL.md and SKILL.toon) and then reads/normalizes that content to drive keep/filter decisions, so untrusted third‑party content could materially influence agent actions.