skills/diego3g/craft/states/Gen Agent Trust Hub

states

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to render and screenshot HTML components. In the HTML adapter, it provides specific command templates for headless Chrome and Playwright, suggesting ways to execute these commands within restricted environments (e.g., using $PWD and avoiding multi-step commands like 'cd' or '&&').
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, potentially untrusted data from a project's codebase and design tools, creating an attack surface where malicious content in those files could influence agent behavior.
  • Ingestion points: Reads project-level files such as 'DESIGN.md', CSS source code, and metadata/components from Figma and Paper MCP servers.
  • Boundary markers: The instructions do not define clear delimiters or markers to isolate content read from external files from the agent's core instructions.
  • Capability inventory: The skill possesses the ability to write HTML files, modify nodes in design tools (Figma/Paper), and execute shell commands via a headless browser for capturing screenshots.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from external design documents or source code files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 10:15 PM