jetson-speculative-decoding

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides configuration instructions for Jetson vLLM deployments, specifically for speculative decoding flags. No malicious behavior was identified in the instructions or metadata.
  • [SAFE]: No hardcoded credentials, sensitive file access, or network exfiltration patterns were detected.
  • [SAFE]: The skill does not involve remote code execution, dynamic code generation, or the installation of untrusted dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 08:45 PM
Security Audit — agent-trust-hub — jetson-speculative-decoding