Skills
Navigate
skills/nexu-io/open-design/swiss-creative-mode-template/Gen Agent Trust Hub

swiss-creative-mode-template

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted external design data to influence its output.
  • Ingestion points: The workflow in SKILL.md requires the agent to read an external DESIGN.md file to map palette, typography, and layout decisions into CSS variables.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined in SKILL.md for the data read from DESIGN.md.
  • Capability inventory: The skill utilizes the file_write capability to create the index.html primary output artifact.
  • Sanitization: There is no evidence of validation or sanitization protocols for the configuration values extracted from the external DESIGN.md file before they are applied to the template.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:49 AM
Security Audit — agent-trust-hub — swiss-creative-mode-template