Git Worktree
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes bash commands including
git worktree,mkdir, andbasenameto manipulate the local filesystem and git configuration. It is configured toalwaysAllowbash execution, which grants the agent permission to run these commands. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it interpolates the
<branch>placeholder directly into shell commands without validation or boundary markers. - Ingestion points: The
<branch>variable inSKILL.mdused for creation and removal operations. - Boundary markers: None identified; the input is treated as a literal shell variable.
- Capability inventory: Commands include
mkdir -pandgit worktree add, which allow filesystem modification. - Sanitization: None; the skill relies on the agent or user to provide a safe branch name string.
Audit Metadata