skills/mastra-ai/mastra/pr-splitter/Gen Agent Trust Hub

pr-splitter

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected. The skill outlines a standard developer workflow for Git branch management and local documentation.
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands for Git operations (e.g., git branch, git diff, git checkout, git restore) and Changeset management (pnpm changeset). These are legitimate uses of the tool's capabilities for repository management.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading Git history and code diffs from the local environment. While this involves processing external data that could contain instructions, the skill does not grant unsafe permissions based on that data, and no specific injection vectors were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 02:35 PM