personal-data-harvester
Fail
Audited by Snyk on Aug 21, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.90). The skill contains deliberate credential-harvesting and stealthy scraping techniques (saving browser cookies, instructing extraction of auth cookies, and patching browser fingerprints) plus persistence instructions for automated, continuous harvesting — enabling stealthy exfiltration or misuse of authenticated sessions.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow includes Playwright automation that visits outsider-authored Douban/Bilibili/Xiaohongshu pages for the user’s own account (e.g., scraping card titles/notes/comments) and parses them into items at runtime.
Issues (2)
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata