capacitor-mcp

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required workflow configures and uses the awesome-ionic-mcp MCP server, which at runtime fetches documentation/demos from multiple public web sources (e.g., ionicframework.com, docs-demo.ionic.io, capawesome.io, capgo.app, capacitiorjs.com) and thus can feed outsider-authored free text into the agent’s LLM context via MCP tool outputs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs runtime execution via npx of the awesome-ionic-mcp MCP server (which is provided by https://github.com/Tommertom/awesome-ionic-mcp), meaning remote code is fetched and executed at runtime and is a required dependency.