accessibility

Pass

Audited by Gen Agent Trust Hub on Jun 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Includes Node.js, Shell, and PowerShell scripts for automating accessibility audits. These tools perform local file system operations, such as scanning for ARIA attributes and creating documentation files, which are standard for development workflows.
  • [EXTERNAL_DOWNLOADS]: The skill documentation points to its official source on GitHub for installation via npx and yarn. These links refer to the vendor's own codebase and infrastructure.
  • [PROMPT_INJECTION]: The skill processes project files to identify accessibility issues. While this exposes a surface for indirect prompt injection where malicious code could attempt to influence the agent, the risk is mitigated by the use of static analysis and the specific instructional scope of the skill.
  • [DATA_EXFILTRATION]: All scripts operate locally and do not initiate network connections or attempt to access sensitive system files (e.g., credentials or SSH keys).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 9, 2026, 03:40 PM
Security Audit — agent-trust-hub — accessibility