The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a variety of shell commands to manage the Git environment and automate setup tasks.
- Evidence: Commands include git worktree add, git branch, git rev-parse, ls, and cd. It also executes build and test commands like npm install, cargo build, pip install, poetry install, and go mod download.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted configuration data from repository files and uses it to trigger code execution through package managers.
- Ingestion points: The skill reads project-level configuration files such as package.json, Cargo.toml, requirements.txt, pyproject.toml, and go.mod (SKILL.md, Step 3).
- Boundary markers: There are no explicit markers or instructions for the agent to ignore potentially malicious instructions embedded within these external files.
- Capability inventory: The skill has the capability to execute package managers and test runners (npm, pip, poetry, cargo, go), which are known to execute build-time code (e.g., preinstall scripts or build macros) defined in the configuration files.
- Sanitization: No sanitization or validation of the configuration file contents is performed before the agent executes the corresponding build or installation commands.

using-git-worktrees