ai-content-humaniser

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md's Hallucination Gate and verification rules explicitly require running web searches and citing/verifying primary sources ("For any output making factual claims, run: 'Use web search to find the latest news and resources, and cite your sources'..." and "Verify every statistic and citation against a primary source"), which mandates ingesting open/public third‑party content that could carry untrusted instructions.