svg-hand-drawn-preview
Warn
Audited by Snyk on Apr 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly accepts an SVG URL as an input (SKILL.md "Accept either: ... an SVG URL") and its required workflow instructs the agent to "Inspect the SVG source first", and the runtime player (assets/player.js) parses data-* attributes from the SVG to control timing/behavior, so arbitrary third-party SVG content could influence agent decisions and tool behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata