skills/knoopx/pi/jujutsu/Gen Agent Trust Hub

jujutsu

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Command Execution] (SAFE): The skill lists standard commands for managing a Jujutsu repository. These operations are restricted to the intended VCS functionality and do not involve suspicious command execution.
  • [Data Exposure] (SAFE): Network commands like 'jj git push' are standard for VCS operations and do not show signs of data exfiltration to unauthorized endpoints.
  • [Indirect Prompt Injection] (SAFE): The skill allows the agent to read potentially untrusted data from commit logs and diffs. 1. Ingestion points: 'jj log' and 'jj diff' outputs. 2. Boundary markers: Absent. 3. Capability inventory: 'jj' CLI commands. 4. Sanitization: Absent. This is a common surface for VCS tools and no malicious exploitation patterns were found.
  • [No Code] (SAFE): No external code, configuration files, or scripts are provided with this skill, reducing the overall attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 03:27 AM