git-worktrees
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes standard shell commands (
git,npm,pip,cargo,go) to manage isolated Git workspaces. While these tools can execute code from the local repository, this behavior is the primary intended purpose of a development automation skill. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill identifies and processes project-specific configuration files (
CLAUDE.md,AGENTS.md) and repository manifests to determine setup steps. - Ingestion points: Local file system reads of
CLAUDE.md,AGENTS.md,package.json,requirements.txt,Cargo.toml, andgo.mod. - Boundary markers: Absent; the skill does not explicitly warn the agent to ignore instructions embedded in these data files.
- Capability inventory: The skill includes instructions to execute shell-based build and test commands (
npm install,cargo build, etc.). - Sanitization: Absent; the skill relies on the integrity of the local repository being managed.
Audit Metadata