monorepo-setup-worktrees
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a unified CLI (
scripts/worktree) that allows the agent to orchestrate Git worktrees and Docker containers, including creating, pausing, resuming, and removing services. - [PROMPT_INJECTION]: The skill provides a framework for the agent to interact with branch code, which constitutes an indirect prompt injection surface.
- Ingestion points: Monorepo and service directories within branch worktrees (e.g.,
~/Editframe/worktrees/<branch>/). - Boundary markers: Absent; the instructions do not specify delimiters or guidelines for handling instructions that might be embedded in the code being processed.
- Capability inventory: Includes shell command execution, file system writes, and database manipulation via provided local scripts like
scripts/worktreeandscripts/smoke-test.ts. - Sanitization: Absent; the agent is expected to operate directly on the files and scripts within the monorepo structure.
Audit Metadata