hig
Warn
Audited by Snyk on Apr 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly directs the agent at runtime to fetch missing Human Interface Guidelines pages from the sosumi.ai Markdown mirror (e.g., https://sosumi.ai/design/human-interface-guidelines/buttons), which would inject remote Markdown into the agent’s context and thus directly control prompts as a required fallback.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata