branch-integration
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell-based git commands and project-specific test suites to perform its core functions. It executes commands such as git rev-parse, git worktree remove, and git worktree prune. This is expected behavior for a repository management tool.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the local repository environment, such as branch names and worktree provenance records, which are potentially attacker-controllable. 1. Ingestion points: Branch names and provenance records in SKILL.md. 2. Boundary markers: Not explicitly defined for variable interpolation. 3. Capability inventory: Execution of git commands and local test suites across the workflow. 4. Sanitization: The risk is mitigated by an interactive workflow that requires explicit human authorization and confirmation before executing test suites or final integrations.
Audit Metadata