krt-interface-warden

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of markdown documentation and configuration files intended to guide UI development. No executable scripts, shell commands, or automated installations were found.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials or sensitive file paths were detected. All external URL references are for documentation purposes and point to well-known design and research platforms.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data in the form of design briefs and contracts to inform code generation. This represents an ingestion surface for potential indirect instructions.
  • Ingestion points: SKILL.md (ingests 'Guardian UX contracts' and 'Inquisitor critique briefs').
  • Boundary markers: Not explicitly defined in the instruction set.
  • Capability inventory: Generation of JSX and CSS frontend code.
  • Sanitization: No explicit sanitization logic is provided within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 06:55 AM
Security Audit — agent-trust-hub — krt-interface-warden