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 install lifecycle hook or concrete malicious behavior. The flagged install is a disclosed, conditional setup action for a related dependency, and the listed agent integrations appear to support local CLI features.
Static reason
One or more suspicious static signals were detected.
Trigger
Running the CLI’s explicit initialization or helper commands.
Impact
These inspected behaviors support the product’s setup and local helper features; no unauthorized control-surface change or data exfiltration was established.
Mechanism
Initialization can install the related code-graph dependency when installation is allowed; the inspected agent helpers read project settings or local session data.
Decision evidence
public snapshot
Evidence for AI clean decision
package.json has no preinstall, install, or postinstall hook.
The listed agent helpers read project or Claude configuration and session data for CLI features; the inspected excerpts show no network send or unconsented configuration mutation.
The Monograph dependency install is disclosed and runs only during initialization when allowed; it targets the related @monoes/monograph package.
The README’s security section describes the product, not instructions aimed at this review.
Doctor shell execution is a command helper; the inspected provider and LSP excerpts show routine CLI functionality.
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 931 files · 6.78 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.