worktree
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill executes standard git commands (git worktree, git branch) to manage worktree lifecycles, which is consistent with its stated purpose and lacks malicious intent.
- [DATA_EXFILTRATION] (SAFE): The skill does not access sensitive local files or perform unauthorized data transmission. Repository metadata access is restricted to git-standard operations.
- [PROMPT_INJECTION] (SAFE): No instructions to bypass security filters, ignore previous instructions, or override agent behavior were identified.
- [Indirect Prompt Injection] (SAFE): The skill processes local git command output, posing a theoretical but standard attack surface for development tools. 1. Ingestion points: git status and git worktree list in WORKFLOWS.md. 2. Boundary markers: Absent. 3. Capability inventory: git worktree, branch management, and remote head checks. 4. Sanitization: Absent.
Audit Metadata