open-autoglm-phone-agent
Warn
Audited by Snyk on Mar 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and reasons over device screenshots ("Input: Screenshot + task description" and examples like "Open Instagram..." and aiQuery), meaning it reads untrusted/user-generated app and web content from third-party apps which can materially influence generated actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata