skills/brijr/skills/craft-ds/Gen Agent Trust Hub

craft-ds

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The 'Prose' component template in SKILL.md and the reference implementations (references/ds-tailwind.tsx and references/ds-css.tsx) use the dangerouslySetInnerHTML property to render content. This creates a vulnerability surface for Indirect Prompt Injection because if the AI processes untrusted data containing malicious HTML or scripts, those payloads will be executed in the user's browser context upon rendering.
  • Ingestion points: The dangerouslySetInnerHTML prop is explicitly exposed in the 'ProseProps' interface and used within the 'Prose' component in all provided files.
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are included in the generated code or templates.
  • Capability inventory: The generated code is restricted to frontend rendering and does not possess capabilities for file system access, network operations, or subprocess execution.
  • Sanitization: The skill lacks any instructions or code patterns for sanitizing input data before it is passed to the unsafe dangerouslySetInnerHTML property.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:39 AM