prospecting

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

• Third-party content exposure detected (high risk: 0.85). The required workflow for this skill (especially the Demand-signal branch) ingests outsider-authored free text from public web sources at runtime—e.g., forum posts, reviews, GitHub issues, and job posts—via “social-fetch/scraping/Firecrawl/Browserbase” that read the original pages into LLM context.