CLI engine for Monomind — an open-source MCP server for Claude Code, OpenCode, Antigravity, Kimi Code, and Codex, with a codebase knowledge graph (tree-sitter + SQLite), persistent memory, multi-agent task coordination, and session hooks. Apache 2.0 licen
Allowed — no malicious behavior detected
20 low-signal patterns reviewed and cleared.
AI security review
scanned · by lpm-firewall-ai
Source inspection found no concrete attack behavior. The flagged package install is part of explicit CLI initialization, and the manifest has no npm install lifecycle hook.
Static reason
One or more suspicious static signals were detected.
Trigger
Importing the package or invoking its CLI; Monograph installation is triggered by the init flow.
Impact
No confirmed malicious effect or unconsented broad agent-control mutation was established.
Mechanism
The manifest has no install lifecycle hook. The reviewed runtime package installation is for the package-aligned Monograph dependency and runs from init post-steps.
Decision evidence
public snapshot
Evidence for AI clean decision
package.json declares CLI entrypoints and no preinstall, install, or postinstall lifecycle hook.
The flagged agent helper paths read Claude project or user agent files and session data for registry, capture, restore, task, status, token, and micro-agent features.
The Monograph dependency installation occurs in the explicit init post-step, and init-action invokes that setup flow.
The remaining flagged paths provide doctor checks, provider configuration, an editor LSP command, and a generated pre-commit hook; inspection found no confirmed attack behavior in them.
README content inspected describes the product and its agent features; no reviewer-directed manipulation was found.
Evidence against
Behavioral surface
SourceChild process · Crypto · Dynamic require · Environment variables · Filesystem · Network · Shell · Web socket
Supply chainHigh entropy strings · URL strings
ManifestNo manifest risk signals triggered.
Scanned 902 files · 6.63 MB of source
37 external domains referenced
127.0.0.1
accounts.google.com
aider.chat
antigravity.google
api.anthropic.com
api.example.com
api.github.com
api.osv.dev
api.z.ai
cdnjs.cloudflare.com
cli.github.com
code.claude.com
code.visualstudio.com
cursor.com
docs.factory.ai
docs.github.com
docs.openclaw.ai
docs.x.ai
example.com
gemini.google.com
git-scm.com
github.com
hermes-agent.nousresearch.com
huggingface.co
kiro.dev
learn.chatgpt.com
monoes.me
nodejs.org
opencode.ai
raw.githubusercontent.com
registry.npmjs.org
services.nvd.nist.gov
www.apple.com
www.instagram.com
www.kimi.com
www.linkedin.com
x.com
Findings
8 high · 7 medium · 5 low
Automated scan signals; the review checked them and cleared this version. Where they are, most severe file first. Code opens a file's flagged lines, with their evidence, below.