igniteui-blazor-components
Warn
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The agent is instructed to automatically modify IDE and application configuration files (such as .vscode/mcp.json, .cursor/mcp.json, and Claude Desktop's JSON config) to register and launch the igniteui-cli MCP server. This modification persists across sessions.
- [EXTERNAL_DOWNLOADS]: The skill's setup instructions rely on npx -y igniteui-cli mcp, which downloads the igniteui-cli package from the public npm registry if it is not found on the local system.
- [REMOTE_CODE_EXECUTION]: The execution of the igniteui-cli tool via npx is a remote code execution pattern. This tool is provided by the vendor (IgniteUI) and is required for the skill's core functionality.
- [PROMPT_INJECTION]: The SKILL.md file contains several 'MANDATORY AGENT PROTOCOL' and 'AGENT INSTRUCTION' blocks that use authoritative commands to steer agent behavior and enforce automatic environment modifications.
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes data retrieved from the igniteui-cli MCP server tools.
- Ingestion points: Documentation content retrieved via the igniteui-cli MCP server (referenced in SKILL.md).
- Boundary markers: The agent context does not specify delimiters or instructions to ignore embedded directives in the retrieved content.
- Capability inventory: The agent has permissions to write to configuration files and generate application code.
- Sanitization: There is no evidence of sanitization or validation performed on the external documentation content before it is processed.
Audit Metadata