using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project files to determine which setup and test commands to execute.
- Ingestion points: Reads project files (package.json, Cargo.toml, requirements.txt, pyproject.toml, go.mod) as specified in SKILL.md.
- Boundary markers: No delimiters or warnings are implemented to ignore instructions potentially embedded in these files.
- Capability inventory: Uses npm, cargo, pip, poetry, and go to install dependencies and run tests, which can execute arbitrary scripts defined in the project files.
- Sanitization: No validation of file content is performed prior to executing the associated package management commands.
- [COMMAND_EXECUTION]: The skill executes multiple shell commands for git management and project-specific build/test tasks.
- [EXTERNAL_DOWNLOADS]: The skill triggers external downloads from package registries via npm, pip, cargo, and go.
Audit Metadata