i18n-accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or binary files. Its functionality is entirely based on natural language instructions for the agent.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source files (HTML/CSS) to perform accessibility audits. While this creates a theoretical surface for indirect prompt injection if the audited content contains malicious instructions, the skill lacks the necessary capabilities (such as file-writing tools or network exfiltration) to be exploited. Evidence chain:
- Ingestion points: Processes external source files during the audit phase.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No subprocess calls, network operations, or file-system modifications were detected.
- Sanitization: No explicit sanitization or filtering of input content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill references authoritative technical documentation and specifications from trusted sources including WHATWG, W3C, RFC Editor, and Unicode. These references are used for auditing guidance and are safe.
Audit Metadata