html
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational, providing guidelines and examples for HTML formatting, accessibility, and semantic structure.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and format HTML code provided by users, which is an ingestion point for untrusted data. However, since the skill only provides formatting guidance and does not possess executable capabilities (such as network access, file system writes, or subprocess execution), the risk is negligible.
- Ingestion points: User-provided HTML code passed to the agent for formatting (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No executable capabilities detected across any files.
- Sanitization: Not applicable as the skill performs static analysis/formatting.
Audit Metadata