form-field-multiple-labels
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and accessibility best practices. No executable code or suspicious patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external HTML content, which is a surface for indirect prompt injection. The risk is assessed as safe as the skill lacks automated execution capabilities or dangerous tools.
- Ingestion points: Rendered HTML and interactive components mentioned in SKILL.md.
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: The skill defines instructions for manual or programmatic review but does not include scripts or network operations.
- Sanitization: No sanitization instructions are provided for the input HTML.
- [EXTERNAL_DOWNLOADS]: The skill references external accessibility documentation from well-known resources such as WebAIM and Deque University for verification.
Audit Metadata