zsxq-shared

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow includes commands that fetch and read public group/topic data from the external 知识星球 service (e.g., "zsxq-cli api raw --method GET --path /v2/groups/123456789/topics" and "zsxq-cli api call search_groups"), which are user-generated/untrusted third‑party contents the agent would ingest and could influence subsequent actions.