worktree

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied 'slug' and 'branch' arguments which are interpolated into shell commands.
  • Ingestion points: User input for 'slug' and 'branch' variables defined in SKILL.md.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are present for the interpolated data.
  • Capability inventory: Execution of shell commands including 'git worktree add', 'git rev-parse', and 'git submodule update' as described in SKILL.md.
  • Sanitization: The skill provides a sanitization procedure for the 'slug' input but lacks explicit sanitization instructions for the 'branch' name before it is passed to shell commands.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various local 'git' commands to manage repository worktrees, which is consistent with its stated developer-focused purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 09:13 PM
Security Audit — agent-trust-hub — worktree