speculative-decoding
Warn
Audited by Snyk on Oct 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: 0.70). The skill executes
git clonefrom external GitHub repositories (https://github.com/FasterDecoding/Medusaandhttps://github.com/hao-ai-lab/LookaheadDecoding) and installs them viapip install -e .during setup, introducing arbitrary third-party code as an operational dependency with weak/unknown provenance.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata