unit-tests

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly points to and instructs fetching a public recipe from fullstackrecipes (recipe://fullstackrecipes.com/unit-tests and https://fullstackrecipes.com/api/recipes/unit-tests), so the agent could ingest untrusted third‑party content that might carry indirect prompt injections.