lfg-alarm

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads public alarms and social comments via tools like browse_discover and read_comments, which can contain outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs connecting to a remote MCP server (https://mcp.lfg.gm) and referencing setup instructions at https://lfg.gm/agents, which are common/reputable unofficial operational dependencies.