Confidence Check

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to use WebFetch/WebSearch/Tavily and to "Search GitHub" and documentation URLs to verify official docs and find OSS references, meaning it will fetch and interpret arbitrary public web and user-generated content (e.g., GitHub, public docs) as part of its workflow.