skills/fusengine/agents/design-ios/Gen Agent Trust Hub

design-ios

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill references established design documentation and community resources (e.g., Apple Developer, ios-resolution.com, iosfontsizes.com). These references are treated as static configuration data for the AI's design tasks and do not involve automated script execution or unverified remote code loading.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied design specifications, which represents a standard ingestion surface.
  • Ingestion points: The skill reads design-system.md to extract color, typography, and motion tokens.
  • Boundary markers: The instructions do not specify the use of delimiters or specific instructions to ignore embedded commands within the input file.
  • Capability inventory: The skill's capabilities are limited to generating HTML/CSS code for mockups and Markdown for documentation. It does not have access to tools for network communication, persistent storage, or shell command execution.
  • Sanitization: The skill does not define specific sanitization or validation logic for the input tokens, which is typical for a design-focused generation task.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 04:07 PM
Security Audit — agent-trust-hub — design-ios