personal-wechat
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s required runtime workflow calls the user-supplied Wisdom HTTP API endpoints (e.g.,
/api/messages,/api/conversations*,/api/search) and then decodes the response body into LLM-readable JSON/strings (scripts/personal_wechat.pyreadsresponse.read()and returnstext/rawwhich is printed), and that response can contain outsider-authored free text (WeChat messages/conversation content) sourced from other people.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata