computer-use
Warn
Audited by Snyk on Sep 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow takes screenshots of the local desktop and GUI apps (which may contain outsider-authored messages from chat apps like Feishu or WeChat) and feeds them into the vision model.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata