agency-accessibility-auditor

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill suggests using npx to run @axe-core/cli and lighthouse. These are well-known and widely trusted industry-standard tools for web accessibility and performance auditing. Their usage here is consistent with the skill's primary purpose.
  • [COMMAND_EXECUTION]: The skill includes instructions for running command-line tools to perform automated accessibility scans. These commands (npx @axe-core/cli, npx lighthouse) are targeting local or specified web environments for auditing purposes and do not represent unauthorized or dangerous execution logic.
  • [INDIRECT_PROMPT_INJECTION]: As an auditor, the skill processes external web content (HTML, ARIA attributes, etc.). While this presents a theoretical surface for indirect prompt injection from malicious websites, the skill's instructions strictly focus on extracting accessibility metadata and success criteria conformance, which significantly mitigates the risk of the agent following instructions embedded in the audited content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:27 AM