base-app-setup

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs fetching Markdown recipes from the public site https://fullstackrecipes.com (via curl to /api/recipes/...), so the agent would ingest untrusted third-party web content that could contain instructions affecting subsequent actions.