brainstorming
Warn
Audited by Snyk on Aug 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). Source and runtime path: the Visual Companion reads user-supplied browser interaction text from
$STATE_DIR/events(written from client-sidetarget.textContentinscripts/helper.js) back into the agent’s next turn pervisual-companion.mdloop.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata