use-fullstackrecipes

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

• Third-party content exposure detected (high risk: 0.70). The skill issues a curl to https://fullstackrecipes.com/api/recipes/use-fullstackrecipes to fetch markdown recipes from a public third-party site, so the agent would ingest and interpret external/untrusted web content that could contain injected instructions.