zsxq-summary

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill programmatically fetches user-generated posts and PDF attachments from the public 知识星球 API (api.zsxq.com) via fetch_topics.js and groups.json-configured group IDs and then automatically parses and uses that untrusted content to produce investment analysis and recommendations as specified in SKILL.md (steps 2–4), so third-party content can materially influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 09:30 AM