html5-semantic-elements
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to review and process external HTML templates, rendered markup, and components. This creates a surface where malicious instructions could be embedded in the data being reviewed.
- Ingestion points: HTML templates, server-rendered HTML, and shared components provided to the agent for review (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the reviewed HTML.
- Capability inventory: The skill is primarily instructional and focused on identification/explanation; it does not invoke subprocesses, write to the filesystem, or perform network operations based on the input.
- Sanitization: No sanitization or escaping of the input markup is specified.
- [SAFE]: The reference documentation includes a link to Cloudflare's CDN (cdnjs.cloudflare.com) to fetch the html5shiv library for legacy browser support, which is a well-known and established service.
Audit Metadata