accessibility-checker

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: Analysis of the skill instructions and metadata found no evidence of malicious intent, prompt injection, or data exfiltration. The instructions focus strictly on accessibility auditing tasks.
  • [NO_CODE]: The skill consists entirely of natural language instructions and documentation. No scripts, binaries, or automated command-line instructions are included within the skill files.
  • [PROMPT_INJECTION]: The skill's primary function involves analyzing external source code for accessibility compliance. This creates a theoretical surface for indirect prompt injection from audited files, though no exploitable capability or unsafe data interpolation was identified.
  • Ingestion points: Audited project files (HTML, CSS, JS) containing UI code.
  • Boundary markers: Absent; the instructions do not specify delimiters or boundary markers for the audited content.
  • Capability inventory: Mentions industry-standard tools (axe, lighthouse), implying command execution of these specific auditing tools.
  • Sanitization: Absent; no content filtering or validation logic is defined for the audited data within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 06:58 AM
Security Audit — agent-trust-hub — accessibility-checker