v-human-app-tester
Warn
Audited by Snyk on Nov 17, 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 systematically reads every screen of an arbitrary installed app via uiautomator XML and screencaps, including all list items and feeds, so outsider-submitted user content displayed in that app (comments, posts, messages) is ingested without the agent selecting a specific item, and external-link taps add arbitrary web content on top.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata