commit-splitter

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands including git stash, git diff, git apply, and git commit to manage the version control workflow.
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script, scripts/extract-hunks.py, to process and extract specific hunks from patch files.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from the repository's files.
  • Ingestion points: Untrusted data enters the agent context through the output of git diff and the resulting hunk summaries.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the workflow.
  • Capability inventory: The skill has the capability to execute shell commands, write to the filesystem (via /tmp), and commit changes to the repository.
  • Sanitization: The helper script validates that hunk selections are integers, but it does not perform sanitization on the content of the diffs themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 07:16 PM