speculative-decoding
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's installation and training steps explicitly git-clone and pip-install repositories (https://github.com/FasterDecoding/Medusa and https://github.com/hao-ai-lab/LookaheadDecoding), which fetch remote code that is then installed/executed and are required dependencies for the skill.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata