react-rendering

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting and rendering untrusted Markdown data from external sources, which constitutes an indirect prompt injection surface.
  • Ingestion points: The Article and UserPost React components in SKILL.md accept a source string prop, which is intended to hold external Markdown content.
  • Boundary markers: The examples do not demonstrate the use of specific delimiters or 'ignore embedded instructions' warnings for the input source.
  • Capability inventory: The skill enables rendering of Markdown content into React nodes and provides an optional allowHtml capability which, when enabled, allows the rendering of raw HTML elements.
  • Sanitization: The skill documentation explicitly warns that the @tanstack/markdown library does not sanitize raw HTML content when the allowHtml flag is set, requiring developers to implement their own sanitization or avoid the feature for untrusted input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 08:33 AM
Security Audit — agent-trust-hub — react-rendering