brainstorming

Warn

Audited by Snyk on Aug 13, 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). Outsider free text can be injected via the Visual Companion’s WebSocket events: the server accepts arbitrary JSON from any authorized client at scripts/server.cjs (handleMessage/handleUpgrade), logs it and appends event objects containing choice to STATE_DIR/events, which the brainstorming workflow then reads on the next turn.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 13, 2026, 06:31 PM
Issues
1
Security Audit — snyk — brainstorming