ai-writing-detection

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs checking and verifying external web citations (see "Layer 5: Citation Verification" and references/citation-patterns.md lines like "Test external links
• do they exist? Search Internet Archive" and "Click DOI links
• do they resolve?"), which requires fetching and interpreting open/public third-party pages whose content could influence detection decisions, so it exposes the agent to untrusted third-party content.