build-quality-tdd

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or risky code executions were detected. The skill instructions are consistent with industry-standard TDD practices.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing potentially untrusted data from browser testing environments, which presents a theoretical attack surface. However, the skill provides explicit safety boundaries and mitigations.\n
  • Ingestion points: Browser testing results including DOM, console logs, and network responses (SKILL.md).\n
  • Boundary markers: Present. The skill explicitly instructs the agent to treat browser content as untrusted data rather than instructions and forbids accessing sensitive tokens.\n
  • Capability inventory: Usage of Chrome DevTools MCP tools for browser-based verification.\n
  • Sanitization: Instruction-based constraints ensure data is processed safely and not executed as code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:47 AM
Security Audit — agent-trust-hub — build-quality-tdd