aria-live-regions
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze and modify project source code that handles dynamic status messages and alerts.
- Ingestion points: Project code identified as containing dynamic content updates, status messages, alerts, or notifications (
SKILL.md). - Boundary markers: Absent; the instructions do not provide explicit delimiters for the agent to separate its own operational instructions from the potentially untrusted project code it is tasked with modifying.
- Capability inventory: The agent is authorized to add and modify ARIA markup (HTML/JSX) and JavaScript logic within the project environment.
- Sanitization: The skill advises developers to "Escape/render untrusted result data safely" in their implementation, but it does not specify sanitization or validation constraints for the agent's own code generation tasks.
- [EXTERNAL_DOWNLOADS]: The skill references external accessibility resources and source materials for developer reference.
- Evidence: The
SKILL.mdfile links to author-owned guidelines in themgifford/ACCESSIBILITY.mdrepository on GitHub, as well as official documentation from MDN (Mozilla), W3C (WAI-ARIA), and WCAG standards.
Audit Metadata