model-checkpoint-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): Analysis of the skill definition revealed no malicious instructions, obfuscation, or unauthorized data access patterns.
  • COMMAND_EXECUTION (SAFE): The skill requests access to Python and Pip via Bash, which is necessary for ML tasks such as model checkpointing and dependency management. No suspicious commands are hardcoded.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:33 PM