research

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Search Strategy" directs executing gemini commands and falling back to a WebSearch tool to fetch open web results, and "Deep Content Analysis" explicitly instructs using docs-seeker to read GitHub repository content—all of which require ingesting untrusted, user-generated or public third-party content that could carry indirect prompt injections.