workflow-worktree
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Git repositories, including repository status, refs, and instructions, which could potentially contain malicious prompts designed to influence the agent's behavior during worktree operations.
- Ingestion points: Repository instructions, status, and refs (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are defined to separate untrusted repository content from the agent's core instructions.
- Capability inventory: Native Git commands for worktree management, including creation, adoption, and retirement (SKILL.md).
- Sanitization: The skill does not explicitly mention sanitization or validation of data read from the repository before it is incorporated into the agent's context.
Audit Metadata