deck-swiss-international

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill functions as a design-constrained document generator.
  • [EXTERNAL_DOWNLOADS]: The example content utilizes well-known and trusted services, including the Tailwind CSS CDN and Google Fonts, for presentation styling.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data access or network transmission was found. The skill operates locally to produce the HTML output.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests user content into an HTML template.
  • Ingestion points: User content is processed to fill the 22 defined layout sections in SKILL.md.
  • Boundary markers: Not explicitly defined in the prompt instructions.
  • Capability inventory: The skill generates static HTML; it lacks subprocess, network, or file-system write capabilities.
  • Sanitization: Not specified in the instructions, though the primary output is text-based HTML for visualization.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:01 PM
Security Audit — agent-trust-hub — deck-swiss-international