aria-meter-name
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs accessibility audits on HTML code. No evidence of credential exfiltration, malicious command execution, persistence mechanisms, or obfuscation was found.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it requires the agent to ingest and analyze untrusted external HTML content.
- Ingestion points: The agent is instructed to review rendered HTML and interactive components (defined in
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores natural language instructions that might be embedded within the audited HTML comments or attributes.
- Capability inventory: The skill utilizes the agent's ability to perform code review and identify specific architectural patterns.
- Sanitization: No sanitization or validation logic is defined to filter the input data before processing.
Audit Metadata