prototype-to-design

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage files across Git branches.
  • Evidence: The skill uses git show to extract design files from a specific branch into a temporary directory for processing (SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external UI prototype files and user-provided identifiers to generate design documentation.
  • Ingestion points: Prototype HTML/CSS files and screen names provided during the handoff process (SKILL.md).
  • Boundary markers: The instructions do not specify delimiters or markers to separate untrusted prototype data from agent instructions.
  • Capability inventory: The skill utilizes file system operations and Git command execution across multiple branches.
  • Sanitization: No explicit validation or sanitization of prototype content is mentioned in the workflow instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:00 PM
Security Audit — agent-trust-hub — prototype-to-design