soia-pkm-clip-wechat-article
Warn
Audited by Snyk on Jul 20, 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). Required runtime path fetches outsider-authored public web content:
scripts/archive_wechat.pycallsfetch_html(url)which downloads the WeChat article HTML from the user-provided URL and then parses/extracts it intoarticle.body/metadata that are written into the vault (and thus become LLM-readable text in the agent’s context via the skill’s outputs/receipts).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata