Skills
skills/ypares/agent-skills/working-with-jj/Gen Agent Trust Hub

working-with-jj

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns or behaviors were identified in the skill documentation or command examples.
  • [Indirect Prompt Injection] (SAFE): The skill processes untrusted data from repository logs (e.g., via jj log), which is an inherent part of its function as a version control helper.
  • Ingestion points: jj log, jj show, and jj file show in SKILL.md.
  • Boundary markers: Absent (raw command output).
  • Capability inventory: Support for jj bisect run in SKILL.md and shell pipelines in references/batch-operations.md.
  • Sanitization: None (standard behavior for documentation).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:13 PM