git-worktree-setup
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands defined within the target repository's documentation and configuration. Specifically, it runs package managers and baseline tests as part of the environment preparation process.
- Evidence: The 'Prepare and Verify' section in SKILL.md instructs the agent to 'Use the repository's package manager and documented command' and 'Run the smallest project-appropriate check'.
- [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by reading and following instructions provided in the repository's setup documents. Malicious instructions in those documents could influence the agent's behavior.
- Ingestion points: Repository setup instructions and configuration files as specified in the 'Prepare and Verify' section of SKILL.md.
- Boundary markers: Absent; no delimiters are defined for repository-sourced content.
- Capability inventory: Shell command execution (package managers, git, and testing tools).
- Sanitization: Absent; the skill does not validate or sanitize instructions read from the repository.
Audit Metadata