tdd

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides conceptual and practical advice on software engineering practices. It does not include executable code, external network calls, or sensitive file access.
  • [DATA_EXPOSURE]: While code examples mention sensitive-looking variables like STRIPE_KEY, these are used strictly as placeholders in educational snippets to demonstrate bad practices (hardcoding) versus good practices (dependency injection). No actual secrets or credentials are present.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read project-specific files like CONTEXT.md. This represents a standard surface for indirect prompt injection common to developer tools, where instructions could be embedded in codebase documentation. However, the skill includes no exploitable logic or unsafe handling of this data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 05:19 PM
Security Audit — agent-trust-hub — tdd