design-fast

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute local Python scripts located in the $HOME/.claude/skills/ui-ux-pro-max/scripts/ directory. These scripts are used to perform search operations for design intelligence across various domains like product, style, typography, and color.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by interpolating user-provided arguments into shell commands.
  • Ingestion points: External data enters the context through the $ARGUMENTS variable within the <tasks> tags in SKILL.md.
  • Boundary markers: The workflow template uses double quotes to wrap the interpolated placeholders (e.g., "<product-type>") in the bash commands.
  • Capability inventory: The skill has the capability to execute subprocesses via python3 and perform file-write operations to update ./docs/design-guidelines.md.
  • Sanitization: There is no evidence of input validation or sanitization of the arguments before they are placed into the command string, which represents a potential command injection surface if the underlying execution environment does not handle shell metacharacters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 03:49 AM