design-system-generate

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx --yes notugly. This allows for the execution of arbitrary code provided by the external notugly package.
  • [EXTERNAL_DOWNLOADS]: The skill relies on downloading and running the notugly package from the public npm registry at runtime. This package does not originate from a well-known or pre-verified service.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to command injection because user-provided data (specifically the <seed> and --brand color) is interpolated directly into shell command templates without explicit sanitization instructions.
  • Ingestion points: User-supplied seed, brand colour, and vibe parameters described in SKILL.md.
  • Boundary markers: None present to delimit user input from the command execution context.
  • Capability inventory: The skill uses npx to execute shell commands based on user input.
  • Sanitization: The instructions lack validation or escaping logic for the interpolated shell arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 05:56 PM
Security Audit — agent-trust-hub — design-system-generate