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
Inspected source supports a benign CLI with explicit project initialization and disclosed installation of a related dependency. Scanner hints about reviewer manipulation and agent control surface changes were not substantiated by the inspected excerpts.
Static reason
One or more suspicious static signals were detected.
Trigger
A user invokes the CLI, such as its init command.
Impact
No concrete malicious effect was established from the inspected behavior.
Mechanism
Initialization may install the related @monoes/monograph dependency when allowed; it reports the install and provides a --no-install option.
Decision evidence
public snapshot
Evidence for AI clean decision
package.json has no lifecycle scripts and exposes CLI entrypoints.
The CLI initializes a project through an explicit init action.
The init flow discloses installing the related @monoes/monograph dependency and offers --no-install to skip.
The agent helper locations inspect or write project-local Claude data and registries; these excerpts show no foreign agent configuration mutation.
The provider command accepts a caller-supplied endpoint alongside a caller-supplied API key; no evidence here shows covert forwarding.
The reviewed README excerpt contains no reviewer-directed instructions; the scanner hint is unsupported by inspected source.
Evidence against
The explicit init flow can run npm install for @monoes/monograph when permitted.
Doctor code uses shell commands, and agent helpers write files, but inspected excerpts do not establish malicious behavior.
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 926 files · 6.76 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.