positioning-truth-tracer

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow ingests competitor messaging scraped/searched from external pages via Firecrawl/Tavily (data sources “Competitor messaging used to re-test the onlyness statement can be pulled… (scrape) or… (search)”) and treats that scraped free text as untrusted input, so an outsider can poison the re-test content it consumes.