ce-worktree

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard Git commands such as git rev-parse, git worktree add, git fetch, and git check-ignore to manage workspace isolation. These commands are necessary for the skill's primary function of setting up worktrees.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external repository data which could potentially contain malicious instructions if the repository is untrusted.
  • Ingestion points: Processes branch names, PR numbers, and repository metadata via Git commands in SKILL.md.
  • Boundary markers: No explicit delimiters or 'ignore' instructions are used when interpolating branch names or PR IDs into commands.
  • Capability inventory: Includes file system modification (writing to .gitignore, creating directories via git worktree) and network operations (git fetch).
  • Sanitization: The instructions do not specify validation for branch names or PR numbers before execution, relying on Git's internal validation of reference names.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:14 AM
Security Audit — agent-trust-hub — ce-worktree