stitch-ui-design-variants

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or unauthorized data access patterns were detected. The skill instructions focus on logic for generating user interface design variations.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted user data to generate prompts.
  • Ingestion points: The skill accepts 'Base Spec' and 'Variant Type' as inputs in SKILL.md.
  • Boundary markers: No delimiters are used to wrap or isolate user-provided specifications from the logic instructions.
  • Capability inventory: The skill is permitted to use stitch*:* (vendor-specific tool), Read, and Write tools as specified in the frontmatter.
  • Sanitization: There is no evidence of input validation or sanitization of the base design specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:04 PM
Security Audit — agent-trust-hub — stitch-ui-design-variants