lovable-i18n

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

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to read third-party MCP connector setup instructions and optionally interact with the Globalize.now platform or CLI tools, but does not monitor or consume outsider-authored free text feeds at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs configuring an external MCP server at https://api.globalize.now/mcp and running npx @globalize-now/cli-client packages during setup and runtime operations, representing a third-party unofficial operational dependency.