discovery-interview

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

• Third-party content exposure detected (high risk: 0.90). The skill's Research Loops explicitly instruct the agent to "spawn an oracle agent or use WebSearch/WebFetch" and even gives examples of gathering findings from public sites (e.g., AllRecipes, Tasty, Paprika), so the agent will fetch and interpret open third‑party web content as part of its workflow, exposing it to untrusted user-generated content and potential indirect prompt injection.