@funny-booth/agent-core@0.1.67
AIエージェント起動CLI(共有ランチャー + MCPサーバー)
AI security review
scanned · by lpm-firewall-aiThe obfuscated feedback module constructs POST reports with tool and target details, HTTP error information, client version and machine metadata. The destination is supplied by portal configuration, and the excerpts do not establish automatic invocation or credential collection, so this is a warning-level telemetry concern.