semantic-html-css
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill audits existing HTML and CSS code, which serves as an entry point for untrusted data. While the primary focus is accessibility auditing, the lack of explicit boundary markers or instructions to disregard embedded comments in the source code creates a surface for indirect prompt injection.
- Ingestion points: Code files provided by the user for auditing (SKILL.md).
- Boundary markers: None identified in the skill instructions to delimit untrusted code from instructions.
- Capability inventory: File reading and potentially editing local source files if requested by the user (SKILL.md).
- Sanitization: No specific sanitization, filtering, or escaping logic is defined for the audited content.
Audit Metadata