ionic-framework-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to utilize the @capawesome/ionic-framework-mcp package from the official npm registry when configuring clients that require local command execution via stdio.
  • [COMMAND_EXECUTION]: The instructions involve running shell commands such as claude mcp add and npx to register the MCP server with the agent's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest documentation and component examples from a remote hosted server (ionic-framework-mcp.capawesome.io), which presents a surface for potential indirect instructions.
  • Ingestion points: Remote content is fetched into the agent's context through the get_doc_page and get_component_usage tools.
  • Boundary markers: There are no explicit delimiters defined to separate the fetched documentation from the agent's system instructions.
  • Capability inventory: The skill leverages subprocess execution capabilities for initial client setup and server proxying.
  • Sanitization: No specific sanitization or filtering logic is described for the content retrieved from the remote documentation server.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 02:00 PM
Security Audit — agent-trust-hub — ionic-framework-mcp