skills/cachemoney/agent-toolkit/jj/Gen Agent Trust Hub

jj

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill instructs the agent to read and process repository content. 1. Ingestion points: File diffs and commit messages via jj diff and jj log. 2. Boundary markers: Agent Rule 5 in SKILL.md requires single-quoting revsets. 3. Capability inventory: VCS mutations (squash, rebase) and potential alias execution via jj util exec. 4. Sanitization: Explicit instructions for shell quoting and avoiding interactive modes.
  • [Prompt Injection] (SAFE): No instructions attempt to override agent constraints or bypass safety filters.
  • [Remote Code Execution] (SAFE): The skill does not download or execute external scripts.
  • [Data Exposure & Exfiltration] (SAFE): No sensitive data access or credential leaks were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 11:27 PM