registry / @funny-booth/agent-core / 0.1.36
@funny-booth/agent-core@0.1.36
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 5d ago · by lpm-firewall-aiThe manifest has no install-time hook; its prepublishOnly script builds and obfuscates the published code. Despite reduced transparency from obfuscation, inspected runtime behavior is consistent with the launcher and portal client, with no concrete malicious behavior identified.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user runs the CLI launcher or MCP server.
Impact
No attack impact was established. Feedback reporting contains tool and error metadata sent through the configured portal client.
Mechanism
The launcher prepares an MCP configuration and starts a child process; the server uses caller-supplied portal settings and standard I/O.
AI rationale
The manifest has no install-time hook; its prepublishOnly script builds and obfuscates the published code. Despite reduced transparency from obfuscation, inspected runtime behavior is consistent with the launcher and portal client, with no concrete malicious behavior identified.
Decision evidence
public snapshotAI called this Clean at 89.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json runs a build and obfuscation step only in prepublishOnly; it declares no install hook.
- The launcher writes an MCP configuration and starts a child process with its environment.
- The MCP server requires a supplied portal URL and token, then starts on standard I/O.
- Feedback reports qualifying tool errors with tool and error metadata through the portal client.
- The published index bundle uses string-table obfuscation, which reduces transparency.
Evidence against
- The published JavaScript is heavily obfuscated, limiting direct review of some implementation details.
Behavioral surface
CryptoDynamicRequireEnvironmentVarsFilesystemNetwork
HighEntropyStringsMinifiedObfuscated
NoLicense
Source & flagged code
5 flagged · loading sourcedist/secretValues.jsView file
7// 受け取るのは Mod（Claude Code の中のプログラム）だけで、AI や会話の記録には渡らない。
L8: const vault_1 = require("./vault");
L9: exports.REDACT_MIN = 6;
Medium
Dynamic Require
Package source references dynamic require/import behavior.
dist/secretValues.jsView on unpkg · L7dist/launcher.jsView file
1'use strict';const _0xf38598=_0x2124;(function(_0x2bf0c2,_0x306dd3){const _0x173dfb=_0x2124,_0x260dfd=_0x2bf0c2();while(!![]){try{const _0x202c13=parseInt(_0x173dfb(0x27b))/0x1*(-p...
High
Same File Env Network Execution
A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/launcher.jsView on unpkg · L1dist/launcher.js#virtual:normalized:round1View file
Findings
1 Critical4 High4 Medium5 Low
CriticalPrevious Version Dangerous Deltadist/index.js
HighSame File Env Network Executiondist/launcher.js
HighCommand Output Exfiltrationdist/launcher.js#virtual:normalized:round1
HighObfuscated Payload Loaderdist/feedback.js
HighObfuscated
MediumDynamic Requiredist/secretValues.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowNo License
Affected versions and remediation
This report applies to @funny-booth/agent-core@0.1.36.
See all versions of @funny-booth/agent-core for other recorded verdicts.
- Review the evidence and your use of @funny-booth/agent-core@0.1.36 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.