agency-accessibility-auditor
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The workflow describes using
npxto fetch and execute@axe-core/cliandlighthousefrom the npm registry. These are well-known, industry-standard tools for accessibility auditing. - [COMMAND_EXECUTION]: The skill provides example shell commands for running automated scans against local or remote web servers to identify accessibility violations.
- [INDIRECT_PROMPT_INJECTION]: The agent is designed to ingest and analyze external web content (HTML, ARIA attributes, and JavaScript behaviors) to perform its auditing role. While this involves processing untrusted data, it is the primary purpose of the skill.
- Ingestion points: Web application content and interfaces under audit (SKILL.md).
- Boundary markers: None specified for the processed content.
- Capability inventory: Shell execution for auditing tools (npx).
- Sanitization: Not explicitly implemented for audited content.
Audit Metadata