breadcrumb-navigation

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill focuses on providing best practices for HTML accessibility and SEO.
  • [PROMPT_INJECTION]: The skill contains an audit instruction to review external templates and rendered HTML, which constitutes an indirect prompt injection surface.
  • Ingestion points: Code review of templates and HTML markup as specified in the Code Review section of SKILL.md.
  • Boundary markers: Absent; the agent is instructed to process the provided code directly for violations.
  • Capability inventory: The skill's operations are limited to analysis and reporting within the agent's output; it does not execute system commands, write to the filesystem, or make external network requests.
  • Sanitization: No sanitization is implemented for the code being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 09:34 AM
Security Audit — agent-trust-hub — breadcrumb-navigation