tdd-parallel

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard testing commands such as pytest, npm test, and php artisan test during the integration phase (Step 4) to verify code changes. This is expected behavior for a TDD-focused skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads layer definitions and scope from an external 'Cycle doc'. This creates a potential surface for indirect prompt injection if the document contains instructions intended to manipulate the agent's behavior.
  • Ingestion points: Cycle doc (referenced in Step 2 of the workflow).
  • Boundary markers: No explicit delimiters or boundary markers were identified in the instructions.
  • Capability inventory: The skill can execute shell commands for testing and invoke other skills (tdd-core:tdd-red, tdd-core:tdd-green, tdd-core:tdd-refactor, tdd-core:tdd-review).
  • Sanitization: No sanitization or validation of the Cycle doc content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:21 AM
Security Audit — agent-trust-hub — tdd-parallel