@funny-booth/agent-core
AIエージェント起動CLI(共有ランチャー + MCPサーバー)
This report shows the evidence for @funny-booth/agent-core@0.1.14. 13 of 37 known versions are blocked or flagged. The newest version, 0.1.41, is flagged. See all versions.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package creates concrete remote code execution and credential exposure paths when its user-facing commands run. Obfuscation and silent global self-updating further remove meaningful user control.
Decision evidence
public snapshot- The published runtime files are deliberately obfuscated, concealing security-sensitive behavior.
- Each salesbot command invokes the launcher, which fetches portal-selected MCP packages and configures them to run through npx.
- The launcher passes its portal token and locally stored secrets into those remotely selected packages.
- An MCP tool accepts a command returned by the portal and executes it with child_process.
- The launcher checks for updates and silently starts a detached global npm installation.
- There is no npm install lifecycle hook; prepublishOnly runs only when publishing.
- The configured portal host is explicit in launcher.config.json.
Source & flagged code
6 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/bin/salesbot7.jsView on unpkg · L2This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/index.jsView on unpkgFindings
Affected versions and remediation
This report applies to @funny-booth/agent-core@0.1.14.
The versions list below shows the verdict for each recorded version.
- Avoid installing @funny-booth/agent-core@0.1.14. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.