grouchygiraffe-ingest

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

• Third-party content exposure detected (high risk: 0.75). At runtime, Step 1 (grouchygiraffe-recipe-lookup) and Step 3 (recipe-cleanup) are expected to fetch and ingest outsider-authored web/social content (e.g., the Instagram post and the author’s recipe page) as readable text into the agent’s LLM context, creating an indirect prompt-injection surface.