food-deep-research

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required runtime workflow includes fetching and reading actual full-text articles via food-fetch/food-research/references/full-text-access.md (open-access downloads, user-provided PDFs, or library session content), which are outsider-authored documents that become readable text in the LLM context during evidence extraction.