read-gzh
Warn
Audited by Snyk on Feb 16, 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 directly fetches and scrapes user-provided WeChat public-account article URLs via scripts/fetch_wechat_article.py and downloads article image URLs (e.g., with curl), so the agent ingests arbitrary, public/untrusted third-party content which it reads and summarizes.
Audit Metadata