igniteui-angular-components

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to download and install several packages from the npm registry, including igniteui-angular, @infragistics/igniteui-angular, igniteui-angular-charts, igniteui-dockmanager, and igniteui-webcomponents. These are legitimate vendor-owned resources for the igniteui platform.
  • [REMOTE_CODE_EXECUTION]: Instructions in SKILL.md and references/mcp-setup.md guide the execution of npx -y igniteui-cli ai-config and npx -y igniteui-cli mcp. These commands download and execute the vendor's CLI tool directly from the npm registry at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill relies on an external MCP server (igniteui-cli) to provide component documentation and API references, creating a surface for indirect prompt injection.
  • Ingestion points: Documentation content retrieved via get_doc, search_docs, and search_api tools is incorporated into the agent's context (specified in SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to treat the retrieved documentation as untrusted data.
  • Capability inventory: The skill identifies components, reads reference files, and generates Angular code based on the retrieved documentation (specified in SKILL.md).
  • Sanitization: No evidence of sanitization or filtering of the external documentation content is present before it is used for code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 12:27 PM