jj

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the jj command-line interface for all version control operations. It also documents the jj util exec feature, which allows for the creation of aliases that execute arbitrary shell commands; however, this is presented with explicit security warnings and is part of the standard functionality of the tool being supported.
  • [PROMPT_INJECTION]: The skill contains specific instructions for the agent to use non-interactive flags (such as -m for commit messages) and to avoid commands that require manual diff selection. These are stability guidelines aimed at ensuring the agent operates reliably within an automated harness, rather than attempts to override system safety filters.
  • [EXTERNAL_DOWNLOADS]: The skill documents standard remote operations such as jj git fetch and jj git push to synchronize with external Git remotes (e.g., GitHub, GitLab). These network operations are intended and necessary for the primary purpose of a version control skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:08 PM