auditing-accessibility-wcag
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and installs established development tools including @axe-core/cli and eslint-plugin-jsx-a11y from the npm registry. These are well-known industry-standard libraries for accessibility testing.
- [COMMAND_EXECUTION]: Provides instructions to execute shell commands using npx to run axe and lighthouse audits against local development servers (localhost:3000). These are standard procedures for developers performing local accessibility checks.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process data from external web pages and components.
- Ingestion points: Web content and component source code targeted by the axe-core and Lighthouse CLI tools as described in Step 1 of the SKILL.md file.
- Boundary markers: Absent; the instructions do not specify delimiters or tell the agent to ignore instructions embedded within the audited content.
- Capability inventory: Includes subprocess execution via npx (Step 1) and report generation (Step 6).
- Sanitization: Not present; the skill does not include steps to sanitize or filter the content of the audited pages before analysis.
Audit Metadata