ai-seo

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and references (e.g., Mode 1 / "AI Visibility Audit" and the monitoring guide) explicitly direct the agent to query and inspect public web sources and platform results (Perplexity, ChatGPT with browsing, Google AI Overviews, Copilot), check robots.txt and cited pages, and then act on those external passages — i.e., the skill requires reading and using untrusted public third‑party content to drive decisions.