text-to-speech
Warn
Audited by Snyk on Mar 7, 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 invokes the inference.sh platform (https://inference.sh) via the infsh CLI (e.g., infsh app run infsh/kokoro-tts), which runs remote apps/logic at runtime so external code is executed and the skill depends on that service.
Audit Metadata