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
The inspected source excerpts support package-aligned CLI and agent-support functionality, with no registry-install lifecycle hook or concrete malicious behavior identified. Static scanner hints alone do not establish an attack.
Static reason
One or more suspicious static signals were detected.
Trigger
The package’s CLI commands or configured agent hooks run.
Impact
No confirmed malicious effect or attack surface was established from these excerpts.
Mechanism
The inspected excerpts show agent registry and session-data reads, project initialization, provider configuration, and editor integration; they do not establish an attack chain.
package.json defines CLI entrypoints and dependencies but no preinstall, install, or postinstall hook.
The cited Claude helper locations read project and user agent, settings, and session data as part of the package’s agent-support features.
The README describes a local-first MCP and CLI tool for Claude Code and other agents.
The cited runtime sources identify Monograph initialization, an environment doctor command, provider configuration, editor LSP integration, helper generation, and the explicit init action.
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 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.