zsxq-topic

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests user-generated content from the knowledge‑sharing platform (e.g., topic +detail, topic +search, and api call get_topic_comments) — public posts and comments in groups — which the agent is expected to read and can influence follow-up actions like replies/answers/edits.