code-apps-design-guide

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Project Setup and Plugin Management: The skill involves the installation of development plugins and the use of environment setup commands such as npx. These are utilized to establish the necessary workspace and scaffold the application using established development practices.
  • External Resource Ingestion: To perform its analysis, the skill fetches content from user-provided URLs using the WebFetch tool. This process allows the agent to extract specific brand information, such as color values and typography, from existing websites or stylesheets.
  • Indirect Prompt Injection Surface: As the skill processes data from external sources, it presents an attack surface where instructions could potentially be embedded in retrieved assets.
  • Ingestion points: Untrusted external data is introduced into the agent's context through the WebFetch tool when analyzing CSS files, websites, or other documents.
  • Boundary markers: The skill's instructions do not currently include explicit delimiters or specific isolation commands to separate the data fetched from external URLs from the agent's primary instruction set.
  • Capability inventory: The skill requires access to tools including Bash, Write, Edit, and TaskCreate, which are used to manage the file system and project lifecycle.
  • Sanitization: The workflow does not explicitly describe sanitization or validation steps for the content retrieved from external URLs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:39 AM
Security Audit — agent-trust-hub — code-apps-design-guide