jujutsu

Warn

Audited by Snyk on Mar 7, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md "Git Integration" section explicitly tells the agent to run "jj git clone " and other git operations, which pulls arbitrary remote git repositories (untrusted, user-generated third-party content) that the agent would read and could materially influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 07:13 AM