create-worktree-skill
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection because it interpolates user-provided branch names directly into tool commands without sanitization.
- Ingestion points: User-provided
branch-nameextracted from the request in Step 1. - Boundary markers: Absent. There are no instructions to validate or wrap the branch name in delimiters.
- Capability inventory:
SlashCommand,Bash,Read,Write,Edit,Glob, andGreptools are available to the agent. - Sanitization: Absent. The branch name is passed directly to the
/create_worktree_promptslash command. - COMMAND_EXECUTION (SAFE): The use of
SlashCommandandBashtools is consistent with the skill's primary intended purpose of managing git worktrees and configuring development environments.
Audit Metadata