using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill automatically executes build and test commands like
make test,npm test, orcargo buildinWORKFLOW.mdandscripts/setup-worktree.sh. These commands run arbitrary scripts defined within the repository's configuration files. - [EXTERNAL_DOWNLOADS]: The skill triggers package managers (
npm,pip,go,uv,cargo) to download dependencies from public registries. While these are well-known services, the downloads are driven by untrusted repository configuration. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by automatically acting on the contents of a checked-out branch.
- Ingestion points: The skill reads repository structure and configuration files (
package.json,Makefile, etc.) inscripts/setup-worktree.sh. - Boundary markers: Absent. The script does not validate the repository content before performing setup and test actions.
- Capability inventory: The skill uses
Bashto executegit,npm,make, and other build tools. - Sanitization: Absent. The skill directly executes commands defined in the repository metadata without sanitization.
Audit Metadata