ling-gui-agent-skill
Warn
Audited by Snyk on Sep 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The agent interacts with the screen and desktop/mobile applications via a GUI driver, which may display outsider-authored content (such as web pages, emails, or chat messages) captured in screenshots and fed into the LLM planner.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata