tdd-workflows-tdd-red

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill includes explicit safety guidelines advising users to keep test data isolated and avoid running tests against production environments.
  • [COMMAND_EXECUTION]: The skill instructs the agent to provide commands to run and verify test failures. This execution is a functional requirement for the TDD workflow and is constrained to the testing environment.
  • [PROMPT_INJECTION]: The skill utilizes the $ARGUMENTS placeholder to ingest user requirements for test generation. This represents an indirect prompt injection surface common to instructional skills.
  • Ingestion points: User-provided requirements passed via the $ARGUMENTS variable in the Prompt Template (SKILL.md).
  • Boundary markers: Absent; user input is interpolated directly into the instruction string.
  • Capability inventory: The skill utilizes the test-automator sub-agent which has capabilities for file generation and command execution for test verification.
  • Sanitization: No explicit sanitization or input validation logic is present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:34 PM
Security Audit — agent-trust-hub — tdd-workflows-tdd-red