brainstorming

Warn

Audited by Snyk on Aug 11, 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 visual-companion runtime writes/reads user-selected text and events via the companion server’s WebSocket flow (browser events JSON from clicks are sent to handleMessage and appended to STATE_DIR/events, which the agent would then read on the next turn), so outsider-authored free text can be ingested without selecting a specific item first.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 12:25 PM
Issues
1
Security Audit — snyk — brainstorming