ai-seo

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md’s activation/runtime workflow instructs the agent to “Read brand/ directory” and to “Use available tools to test AI visibility” via browser/web search (e.g., Perplexity/Google/ChatGPT queries), which can ingest outsider-authored free text from fetched web pages or search results into the LLM context.