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 registry install lifecycle hooks or concrete attack behavior. The flagged setup and agent integration code is consistent with user-invoked CLI functionality, so the package is clean.
Static reason
One or more suspicious static signals were detected.
Trigger
The user invokes the CLI, including its project initialization command.
Impact
No confirmed unauthorized mutation, credential exposure, or other attack was established.
Mechanism
The inspected helpers read project and Claude configuration or registry data; optional dependency installation is disclosed in the initialization flow.
Decision evidence
public snapshot
Evidence for AI clean decision
The manifest identifies this as a CLI and lists no preinstall, install, or postinstall hook; it also names the package-owned agent helpers and configuration files.
The inspected agent helpers read project or Claude configuration and registry data for routing, status, and session support; the inspected excerpts show no credential exfiltration or control hijack.
The post-init code discloses an optional Monograph dependency install, and the init flow invokes it during project initialization.
The README excerpt inspected contains product and workflow information; searches found no reviewer-directed text.
The inspected command excerpts describe provider management and environment checks; no concrete malicious behavior was established.
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 923 files · 6.75 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.