brainstorming

Warn

Audited by Snyk on Aug 14, 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 serves and watches HTML screens from the project’s screen_dir/content directory, and the agent reads/parses user-provided interaction text indirectly via WebSocket events written to state_dir/events (e.g., click text) that can contain arbitrary free text.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 12:13 PM
Issues
1
Security Audit — snyk — brainstorming