accordion-accessibility

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code snippets (templates, HTML, React components) provided by the user. This establishes a surface for indirect prompt injection. However, the risk is minimal as the skill's capabilities are confined to providing explanations and flagging accessibility violations, without access to sensitive system resources, file-writing capabilities, or network operations.
  • [EXTERNAL_DOWNLOADS]: The skill references frontendchecklist.io, which is a well-known and reputable service for front-end best practices. These references are used for documentation purposes and do not involve executable code downloads.
  • [SAFE]: The code examples provided for React and HTML implementation are standard and follow accessibility best practices (e.g., WAI-ARIA Authoring Practices). No malicious patterns such as obfuscation, credential harvesting, or persistence mechanisms were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 10:54 PM