docs-features

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides core documentation features, such as callouts and heading collection, within the TanStack ecosystem. No malicious behaviors or safety guideline violations were detected during analysis.- [EXTERNAL_DOWNLOADS]: The skill references and depends on official packages from the TanStack organization, specifically @tanstack/markdown and @tanstack/highlight. These are legitimate resources that align with the skill's purpose and author.- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted Markdown content to generate metadata and HTML.
  • Ingestion points: The parseMarkdown and renderHtml functions ingest raw markdown source strings.
  • Boundary markers: The skill utilizes specific comment-based delimiters such as <!-- ::start:tabs --> to scope processing.
  • Capability inventory: The skill transforms markdown into structured JSON metadata and HTML custom elements.
  • Sanitization: According to the documentation, JSON-serialized properties are escaped during HTML rendering to prevent attribute-based injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 08:33 AM
Security Audit — agent-trust-hub — docs-features