zsxq-topic
Warn
Audited by Snyk on May 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-generated content from the public 知识星球 service (see references/zsxq-topic-search.md, references/zsxq-topic-detail.md and the API call get_topic_comments) and requires the agent to inspect that content as part of workflows (confirming topic content before answering/replying/deleting), so untrusted third‑party content can influence subsequent tool use and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata