feature-flags-setup

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs fetching a public recipe from an external URL (https://fullstackrecipes.com/api/recipes/feature-flags-setup), meaning the agent would ingest content from an untrusted third-party web source that could contain indirect prompt injections.