skills/nvidia/skills/split-pr/Gen Agent Trust Hub

split-pr

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard version control and repository management tools (git and gh CLI) to perform operations within the scope of the NVIDIA/Megatron-LM repository.
  • [SAFE]: Explicit instructions are provided to push branches to the user's fork and create PRs as drafts, adhering to secure contribution workflows.
  • [SAFE]: The workflow incorporates a mandatory user approval step before any commits or PR creations are executed, preventing unauthorized or unintended changes.
  • [SAFE]: No evidence of credential harvesting, unauthorized data exfiltration, or obfuscation was found in the skill's instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 05:48 PM
Security Audit — agent-trust-hub — split-pr