skills/sickn33/agentic-awesome-skills/accessibility-compliance-accessibility-audit/Gen Agent Trust Hub
accessibility-compliance-accessibility-audit
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content by visiting user-provided URLs and inspecting HTML elements such as alt text, headings, and form labels. Evidence: Ingestion points are located in resources/implementation-playbook.md using puppeteer and axe-core. Capability inventory: Browser automation and structural analysis of DOM elements. Sanitization: Audit results are mapped to structured reports, which limits the risk of the agent interpreting data as instructions.
- [EXTERNAL_DOWNLOADS]: The implementation playbook includes CI/CD examples that fetch standard dependencies and official GitHub Actions. Evidence: References actions/checkout, actions/setup-node, and standard NPM packages like puppeteer, axe-core, and pa11y in resources/implementation-playbook.md.
Audit Metadata