tdd
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local shell commands to execute standard Ruby on Rails development tools, including
bundle exec rspec,bundle exec rubocop, andbundle exec brakeman. These operations are restricted to the local development environment and are central to the skill's stated purpose of facilitating test-driven development. - [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which could potentially contain malicious instructions intended to influence agent behavior.
- Ingestion points: The agent loads project context including schema, routes, and existing patterns in Phase 1, and reviews PR diffs in Phase 4.
- Boundary markers: None explicitly defined in the instruction text to isolate external data from system instructions.
- Capability inventory: The agent has the capability to modify local files and execute shell commands within the project environment.
- Sanitization: The skill enforces a "User Approval" gate in Phase 2, requiring explicit confirmation of proposed implementation changes before they are applied, which serves as a critical human-in-the-loop safety control.
Audit Metadata