wechat-summary

Warn

Audited by Snyk on Mar 9, 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's SKILL.md explicitly instructs using WebFetch on user-provided mp.weixin.qq.com links (and the included scripts/fetch_article.py uses requests.get) to retrieve and parse public WeChat article content, which the agent then reads and interprets to generate summaries—thus ingesting untrusted third-party content that could carry embedded instructions influencing its output.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill fetches user-supplied mp.weixin.qq.com article URLs at runtime (via WebFetch and a fallback script scripts/fetch_article.py which calls requests.get) and injects the retrieved article content into the model context to drive summarization, so mp.weixin.qq.com content can directly control agent prompts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 12:12 AM
Security Audit — snyk — wechat-summary