tdd-expert

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run local repository scripts like python3 tools/quality_gate.py test and git diff --check. These are expected development actions within the defined scope.
  • [PROMPT_INJECTION]: The skill ingests data from local repository files (AGENTS.md, QUALITY.md), creating an indirect injection surface. This risk is mitigated by explicit operational boundaries and the localized nature of the automation.
  • Ingestion points: AGENTS.md, QUALITY.md, and tests/ directory.
  • Boundary markers: Behavioral constraints and stop conditions are defined to limit agent autonomy.
  • Capability inventory: Execution of project-specific Python tools and git commands.
  • Sanitization: Input data is expected to be part of the trusted repository environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 11:25 PM
Security Audit — agent-trust-hub — tdd-expert