ai-rag

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Tool/Model Recommendation Protocol" in SKILL.md explicitly requires reading data/sources.json (curated external references) and verifying 1–2 primary documents per recommendation (release notes, benchmarks, docs), which entails fetching and interpreting open/public third‑party web content that can directly influence the agent's recommendations.