computer-use
Fail
Audited by Snyk on Aug 24, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). The skill and interface explicitly enable unrestricted local UI automation and arbitrary code execution (node_repl, AppleScript, osascript, JXA, etc.) with no confirmation or safety checks, allowing easy credential theft, data exfiltration (access to accessibility text and screenshots), unauthorized logins/installs/deletions, and remote-control style abuse.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests first-party UI accessibility text/screenshot content returned by
sky.get_app_state({app: ...}).text(and optionallyscreenshot.url), which is derived from whatever content the user/attacker has placed into the targeted local app UI.
Issues (2)
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata