igniteui-angular-generate-from-image-design

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes design images (screenshots, mockups, wireframes) provided by the user to generate Angular components. This creates a surface for indirect prompt injection if an image contains text designed to override agent instructions.
  • Ingestion points: User-provided design images as specified in the skill's trigger conditions and Step 1 of the workflow.
  • Boundary markers: The instructions do not specify any delimiters or warnings to ignore text content found within the design images.
  • Capability inventory: The skill allows for file system writes (Angular views), execution of vendor CLI tools (igniteui-cli), and interaction with MCP servers.
  • Sanitization: There is no evidence of text sanitization or filtering for content extracted from images via OCR or similar processes.
  • [COMMAND_EXECUTION]: The skill suggests running npx -y igniteui-cli ai-config to configure the environment. This command executes the vendor's CLI tool directly from the npm registry.
  • [EXTERNAL_DOWNLOADS]: The use of npx for configuration involves downloading a package from the public npm registry at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 12:27 PM