Loading npm security reports…
Loading npm security reports…
@monoes/monomindcli@2.19.0: Clean npm security report (Allow) | LPM Firewall
npm / @monoes/monomindcli / 2.19.0
@monoes/monomindcli@2.19.0 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
21 low-signal patterns reviewed and cleared.
AI security reviewscanned on Oct 9, 2026, 05:54 UTC · by lpm-firewall-ai Source inspection found no install-time execution or concrete malicious behavior. The flagged agent integrations are local project/session features, while installation and setup behavior is absent or user-command driven.
Static reason
One or more suspicious static signals were detected.
Trigger
No attack trigger identified; the doctor repair and project initialization behavior require running their CLI commands.
Impact
No malicious impact was established from the inspected source.
Mechanism
The inspected code reads local project, agent, and session data and builds local registries or helper files; it does not establish unconsented install-time control-surface mutation.
Decision evidencepublic snapshot Evidence for AI clean decision
package.json defines build and release scripts but no preinstall, install, or postinstall hook.
Agent registry and skill registry code reads project or user definitions and builds local registries.
The session handlers inspect project-session data and helper files; the cited settings access is local.
Token tracking scans local Claude project sessions; helper scripts generate a project agent router.
The doctor install operation is an explicit repair command, and crash reporting state distinguishes enabled and disabled choices.
README describes the package's own security feature; inspection found no reviewer-directed instruction. Behavioral surface
Source Child process · Crypto · Dynamic require · Environment variables · Eval · Filesystem · Network · Shell · Web socket
Supply chain High entropy strings · URL strings
Manifest No manifest risk signals triggered.
Scanned 967 files · 7.07 MB of source
38 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 pi.dev raw.githubusercontent.com registry.npmjs.org services.nvd.nist.gov www.apple.com www.instagram.com www.kimi.com www.linkedin.com x.com Findings8 high · 7 medium · 6 low Source & flagged code14 flagged The lines the automated scan flagged. The review checked them and cleared this version.
High AI reviewer manipulationCleared
Package text addresses the security reviewer or scanner and tries to influence the review outcome.
README.md View on unpkg Scanner record · 1 line isSafe('Ignore all previous instructions'); // → false (~0.04ms)
High Child processCleared
Package source references child process execution.
dist/src/init/init-post-steps.js View on unpkg · L46 Code excerpt · 3 lines 46 }
47 const { spawn } = await import ('node:child_process' );
48 const logPath = path.join (outputDir, 'build.log' );
dist/src/commands/doctor-env-checks.js View file High ShellCleared
Package source references shell execution.
dist/src/commands/doctor-env-checks.js View on unpkg · L19 Code excerpt · 3 lines 19 export const MAX_DOCTOR_BUILD_LOG_SCAN_BYTES = 64 * 1024 ; // 64 KB
20 const execAsync = promisify (exec);
21 export async function runCommand (command, timeoutMs = 5000 , env = {}) {
High Runtime package installCleared
Package source invokes a package manager install command at runtime.
dist/src/commands/doctor-env-checks.js View on unpkg · L351 Code excerpt dist/src/orgrt/cline-runner-scoped.js View file Low EvalCleared
Package source references a known benign dynamic code generation pattern.
dist/src/orgrt/cline-runner-scoped.js View on unpkg · L92 Code excerpt · 3 lines 92 /** Whether a scoped turn may run this edit (see EDIT_CHECK_JS). */
93 export const editAllowedInWorkspace = new Function ('fs' , 'path' , `${EDIT_CHECK_JS}\nreturn (name, input, workspace) => editAllowedInWorkspace(name, input, workspace, fs, path);` )(f...
94 /** Start of every refusal the plugin returns (and the ACP rejection names). */
dist/src/init/codex-generator.js#virtual:normalized:round1 View file Medium Dynamic requireCleared
Package source references dynamic require/import behavior.
dist/src/init/codex-generator.js#virtual:normalized:round1 View on unpkg · L37 Code excerpt · 3 lines 37 }
38 /** Generate the project-local adapter used by Codex"s native hook runner. */\nexport function generateCodexHookScript() {\n return `// Monomind native Codex hook bridge (genera...
39 }
Low Weak cryptoCleared
Package source references weak cryptographic algorithms.
dist/src/services/crash-reporter.js View on unpkg · L19 Code excerpt · 12 lines 19 */
20 import { execFile } from 'node:child_process' ;
21 import { createHash } from 'node:crypto' ;
⋯
119 // GitHub's side, which just degrades to "no match found", not a security issue.
120 const { stdout } = await execFileAsync ('gh' , [
121 'issue' ,
⋯
131 ], { timeout: 8000 });
Medium Install persistenceCleared
Source writes installer persistence such as shell profile or service configuration.
dist/src/commands/org-serve.js View on unpkg · L33 Code excerpt · 12 lines 33 export const supervisorAction = async (ctx) => {
34 const cwd = resolve (ctx.cwd || process.cwd ());
35 const requested = String (ctx.flags.format ?? '' )
⋯
37 .toLowerCase ();
38 const format = requested || (process.platform === 'darwin' ? 'launchd' : 'systemd' );
39 if (format !== 'launchd' && format !== ) {
High Cloud metadata accessCleared
Source reaches cloud instance metadata or link-local credential endpoints.
dist/src/commands/providers.js View on unpkg · L6 Code excerpt · 12 lines 6 */
7 import { spawnSync } from 'node:child_process' ;
8 import { output } from '../output.js' ;
⋯
40 output.printError ('Provider name is required. Use -p <name> or pass as first argument.' );
41 return { success: false , exitCode: 1 };
42 }
43 const cwd = process.cwd ();
44 const config = configManager. (cwd);
High Copied package dependency bridgeCleared
Package metadata claims a different repository identity while copied source loads a runtime dependency bridge.
dist/src/commands/monograph-lsp.js View on unpkg · L25 Code excerpt · 4 lines package = @monoes/monomindcli; repositoryIdentity = monomind; dependency = @monoes/monograph
25 try {
26 const { openDb } = await import ('@monoes/monograph' );
27 const { startLspServer } = await import ('@monoes/monograph/lsp' );
dist/src/init/helpers-core-scripts.js View file High External AI agent control surface mutationCleared
Runtime or CLI source writes behavior-bearing configuration into a user or project AI-agent control surface.
dist/src/init/helpers-core-scripts.js View on unpkg Scanner record · 29 lines Runtime or CLI code links a write operation to an explicit external AI-agent control path:
ession.metrics)}\`);
return session;
},
update: (key, value) => {
if (!fs.existssync(session_file)) {
console.log('no active session');
return null;
}
const session = json.parse(fs.readfilesync(session_file, 'utf-8'));
session.context[key] = value;
session.updatedat = new date().toisostring();
fs.writefilesync(session_file, json.stringify(session, null, 2));
dist/src/orgrt/aider/monomind_aider_shim.py View file Medium Ships build helperCleared
Package ships non-JavaScript build or shell helper files.
dist/src/orgrt/aider/monomind_aider_shim.py View on unpkg Scanner record · 4 lines path = dist/src/orgrt/aider/monomind_aider_shim.py
kind = build_helper
sizeBytes = 19323
magicHex = [redacted]
dist/src/commands/init-action.js#virtual:normalized:round1 View file High Semantic analysis limitedCleared
A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
dist/src/commands/init-action.js#virtual:normalized:round1 View on unpkg Scanner record · 1 line stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 22
Cleared
Package metadata 7 findings
Medium Network Cleared
Medium Environment variables Cleared
Medium Structural risk force deep review Cleared
Low Scripts present Cleared
Low High entropy strings Cleared
· 3 lines
351 // npm's output goes to stderr: under `doctor --json` stdout is the JSON.
352 execSync ('npm install -g @anthropic-ai/claude-code' , {
353 encoding: 'utf8' ,
132
const issues = JSON.parse (stdout);
133 const match = issues.find ((i) => i.title === title);
144 async function createIssueViaToken (repo, title, body, token) {
145 const res = await fetch (`https://api.github.com/repos/${repo}/issues` , {
'systemd'
54 // The hash keeps it unique for two directories with the same basename; the
55 // basename keeps it recognisable in `launchctl list` / `systemctl --user`.
56 const slug = `${(cwd.split(/[\\/]/).pop() || 'org').replace(/[^A-Za-z0-9._-]/g, '-')}-${createHash('sha256').update(cwd).digest('hex').slice(0, 8)}` ;
101 if (ctx.flags.install === true ) {
102 const home = process.env.HOME || process.env.USERPROFILE || '' ;
getConfig
127 const key = process.env.ANTHROPIC_API_KEY || getConfigApiKey ('anthropic' );
154 const entry = configuredProviders.find ((p) => typeof p.name === 'string' && p.name.toLowerCase () === 'ollama' );
if (!fs.existssync(session_file)) {
const session = json.parse(fs.readfilesync(session_file, 'utf-8'));
if (session.metrics[name] !== undefined) {
fs.writefilesync(session_file,