motion-design-html
Warn
Audited by Snyk on Nov 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow pulls outsider-authored media (Mixkit/Pexels/Unsplash assets, YouTube meme search results, and user-supplied reference videos or brand sites) into the agent's context, but only after the agent actively searches for or selects a specific item, so the attacker can publish but cannot force delivery.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The decisive boundary is the 21st.dev MCP endpoint, whose
get_componentresponses supply React component code that the skill directs the agent to port into its engine, and 21st.dev is a third-party community registry without established first-party provenance, so the tier is medium.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata