blutui-canopy-blocks

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a framework for processing and rendering data provided by content editors and external data collections, which represents an ingestion surface for untrusted content.\n- Ingestion points: Template data enters through the settings object and collection types described in rules/settings.md.\n- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate editor-controlled data from the rendering logic.\n- Capability inventory: The system supports the inclusion of custom CSS and JavaScript via dedicated head and scripts sections in block templates, as documented in rules/block-templates.md.\n- Sanitization: Guidelines in rules/settings.md and rules/patterns.md recommend using the |raw filter for rich text settings, which bypasses default output escaping to facilitate the rendering of HTML content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 08:59 PM
Security Audit — agent-trust-hub — blutui-canopy-blocks