quality

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow appears to perform LLM-based analysis of a “page content”/“rule page” (e.g., Rule page: https://frontendchecklist.io/...), which implies it may ingest free-form text fetched from an outsider-authored public web page into the agent’s LLM context via the provided URL/content.