aria
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web interface content (HTML) to audit and fix ARIA attributes. This creates a vulnerability surface where malicious instructions embedded in the HTML elements being analyzed could attempt to influence the agent's behavior.
- Ingestion points: Interactive and dynamic elements within the user interface (SKILL.md).
- Boundary markers: None identified in the instructions.
- Capability inventory: Capability to modify files ("fix ARIA attributes") is implied by the skill description.
- Sanitization: No explicit sanitization or validation of the ingested HTML content is mentioned.
Audit Metadata