krt-frontend-ux-guardian

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted data, specifically frontend source code, routing logic, and component definitions from a user's repository.
  • Ingestion points: The skill instructions in SKILL.md (Workflow Step 1) require the agent to inspect the existing frontend framework, routes, data flow, components, and permissions.
  • Boundary markers: The instructions do not define boundary markers or provide 'ignore instructions' warnings for content found within the analyzed repository files.
  • Capability inventory: The skill instructs the agent to read and modify repository files and, according to references/frontend-verification.md, encourages starting local development servers and performing browser-based verification, which creates an execution context for code within the repository.
  • Sanitization: There are no mentions of sanitizing or filtering instructions that might be embedded in code comments, documentation, or data fixtures within the processed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:05 PM
Security Audit — agent-trust-hub — krt-frontend-ux-guardian