ai-seo

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires fetching and inspecting public third-party content (e.g., "Check robots.txt at yourdomain.com/robots.txt" and "Manually test your target queries on each platform" — Perplexity, ChatGPT, Google AI Overviews, Copilot) and the monitoring/visibility guides (references/monitoring-guide.md) instruct manual retrieval and analysis of open web search results, so untrusted web content directly informs the agent's decisions and next actions.