brainstorming
Warn
Audited by Snyk on Aug 27, 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 brainstorming skill’s optional “Visual Companion” runtime serves local HTML and ingests user click text/selected option content via WebSocket into
$STATE_DIR/events, so outsider-authored free text can reach the agent through browser interaction event payloads.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata