@whalent/agent-core@0.3.482
Core runtime for Whalent Agent
AI Security Review
scanned 22d ago · by lpm-firewall-aiThe inspected source supports a warning for explicit MCP-driven agent configuration mutation. It does not establish malware behavior or the install-time conditions required for blocking.
Static reason
One or more suspicious static signals were detected.
Trigger
An MCP tool request selecting skill installation or server registration.
Impact
Requested operations can persist instructions or server configuration affecting later agent sessions; malicious intent was not established.
Mechanism
Downloads skill files into selected agent directories or writes supplied server commands into agent configuration.
AI rationale
The inspected source supports a warning for explicit MCP-driven agent configuration mutation. It does not establish malware behavior or the install-time conditions required for blocking.
Evidence
dist/mcp.cjs.claude.cursor.claude.jsonconfig.tomlopencode.json
Decision evidence
public snapshotAI called this Suspicious at 87.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The MCP request handler exposes action-driven skill installation and agent configuration mutation.
- Skill installation downloads platform content and can write into machine-wide agent skill directories, including .claude and .cursor.
- MCP registration accepts command arguments and writes agent configuration through platform-specific helpers.
- package.json contains no install lifecycle hooks or runtime self-dependency.
Evidence against
- The inspected mutations are activated by MCP tool requests; no automatic npm installation attack was established.
- No concrete covert credential export or malicious payload execution was established.
Behavioral surface
CryptoDynamicRequireEnvironmentVarsEvalFilesystemNetwork
HighEntropyStringsMinifiedObfuscatedUrlStrings
Source & flagged code
7 flagged · loading sourcedist/mcp.cjsView file
1#!/usr/bin/env node
L2: 'use strict';var a0_0x17fa7e=a0_0x49fb;(function(_0x1e995a,_0x1cd5f3){var _0x4cea3a=a0_0x49fb,_0x388594=_0x1e995a();while(!![]){try{var _0x5a8a14=parseInt(_0x4cea3a(0xd03))/0x1+par...
L3: || (${_0x27a557} == "string" && ${_0xcee33} && ${_0xcee33} == +${_0xcee33})`)['assign'](_0x368f64,(0x0,_0x51c059['_'])`+${_0xcee33}`);return;case _0x3207bf(0x20b5):_0x5c8688[_0x320...
High
Obfuscated Payload Loader
Source contains an obfuscated payload loader that reconstructs and executes hidden code.
dist/mcp.cjsView on unpkg · L1•stage = ast_semantic_analysis; reason = ast_path_work_budget_exceeded; limitedFiles = 1
High
Semantic Analysis Limited
A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
dist/mcp.cjsView on unpkg4|| (${_0x27a557} === "string" && ${_0xcee33} && ${_0xcee33} == +${_0xcee33} && !(${_0xcee33} % 1))`)['assign'](_0x368f64,(0x0,_0x51c059['_'])`+${_0xcee33}`);return;case _0x3207bf(0...
L5: || ${_0x27a557} === "boolean" || ${_0xcee33} === null`)[_0x3207bf(0x22c8)](_0x368f64,(0x0,_0x51c059['_'])`[${_0xcee33}]`);}}}function _0x75e093({gen:_0x14b8c5,parentData:_0x5b970b,...
L6: missingProperty: ${_0x1fcf09},
Medium
Findings
3 High7 Medium5 Low
HighObfuscated Payload Loaderdist/mcp.cjs
HighObfuscated
HighSemantic Analysis Limiteddist/mcp.cjs
MediumDynamic Requiredist/mcp.cjs
MediumNetwork
MediumEnvironment Vars
MediumShips Build Helperdist/jupyter_sidecar.py
MediumOversized Source Filedist/index.cjs
MediumOversized Cli Entrypointdist/index.cjs
MediumStructural Risk Force Deep Review
LowEvaldist/mcp.cjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowNo License
Affected versions and remediation
This report applies to @whalent/agent-core@0.3.482.
See all versions of @whalent/agent-core for other recorded verdicts.
- Review the evidence and your use of @whalent/agent-core@0.3.482 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.