@funny-booth/agent-core@0.1.24
古い版です。最新版を使ってください
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 10d ago · by lpm-firewall-aiThe launcher automatically installs a newer global package release in the background when launched. This can install and run new package code without approval, but no malicious payload or other concrete attack was established.
Decision evidence
public snapshot- The package exposes CLI entrypoints that invoke the launcher.
- On launcher startup, the code fetches latest-version metadata for its configured or default package and compares it with the current version.
- When a newer version is reported, the launcher starts a detached global npm install without an approval prompt.
- The update path is conditional on a newer version being reported, and the inspected source does not establish a malicious payload.
Source & flagged code
7 flagged · loading sourcePackage source references child process execution.
dist/mcpPackages.jsView on unpkg · L1Source contains an obfuscated payload loader that reconstructs and executes hidden code.
dist/feedback.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @funny-booth/agent-core@0.1.24.
See all versions of @funny-booth/agent-core for other recorded verdicts.
- Review the evidence and your use of @funny-booth/agent-core@0.1.24 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.