unknowns-discovery

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow is about inspecting “the territory” (e.g., code paths, docs, data, screenshots, references, internet sources, prior work) and explicitly includes searching territory (e.g., “Search for hidden constraints: prior attempts… migrations, auth/permission paths…”) in workflow procedures, meaning outsider-authored text can be ingested if it is present in those inspected sources.