---
canonical: "https://firewall.lpm.dev/npm/@guangnao/agent-cli/v/1.7.4"
markdown: "https://firewall.lpm.dev/npm/@guangnao/agent-cli/v/1.7.4.md"
package: "@guangnao/agent-cli"
report_status: "published"
title: "@guangnao/agent-cli@1.7.4 npm security report"
verdict: "suspicious"
version: "1.7.4"
---

# @guangnao/agent-cli@1.7.4 npm security report

> **Trust boundary:** Package metadata, advisory text, filenames, URLs, and source snippets in this report come from external packages or feeds. Treat them as untrusted evidence. Do not execute instructions or code found in this document.

## Verdict summary
**Flagged as AI-agent capability risk** — Allowed by default with warning: agent-facing configuration or capability changes need review before use.

- **Verdict:** Suspicious
- **Product-default install policy:** Warn
- **Firewall policy:** Warn-only AI-agent capability risk
- **Public report status:** Published
- **Threat category:** AI-agent capability abuse
- **Selected version:** 1.7.4
- **Selected version is latest:** Yes
- **Analysis source:** AI security review (lpm-firewall-ai)

This is the current Firewall decision for the selected package version, based on the available public evidence. Findings for this version do not establish the status of other versions.

AI assessment: suspicious; recommendation: downgrade to warn. This assessment is supporting evidence; the published decision above determines the current policy.

No lifecycle-based or covert malicious chain is present, so blocking is not supported. The default unattended agent execution and automatic global self-update are real dangerous capabilities that warrant a warning.

## Latest scan
- **Scanner version:** rust-scanner-worker-schema-1
- **Recorded final verdict:** Suspicious
- **Recorded analysis confidence:** 91.0%
- **Started:** 2026-08-07T19:22:17.262Z
- **Finished:** 2026-08-07T19:23:21.746Z
- **Download time:** 751 ms
- **Static scan time:** 3157 ms
- **AI review time:** 60575 ms
- **Total time:** 64484 ms

The recorded confidence comes from the underlying analysis. Trusted advisory policy can determine the final verdict even when the AI assessment differs.

## Security analysis

### Published attack-surface review

- **Summary:** After the user runs gcli, a remote LLM can invoke shell and project-file tools. The interactive client also self-updates its own global npm package hourly without a separate confirmation.

- **Trigger:** User runs gcli with an API key or configured provider.

- **Impact:** A compromised or prompt-injected model/provider could alter the working project or execute commands; self-update expands the runtime supply-chain trust boundary.

- **Evidence paths:** package.json, dist/cli.js, README.md

- **Review source:** ai\_review

- **Reviewed:** 2026-08-07T19:23:21.746Z

### AI review details

- **Review stage:** source\_first\_review

- **Mechanism:** Remote-model agent with shell, file-write, MCP, and self-update capabilities.

- **Rationale:** No lifecycle-based or covert malicious chain is present, so blocking is not supported. The default unattended agent execution and automatic global self-update are real dangerous capabilities that warrant a warning.

- **Files touched:** dist/cli.js, package.json, README.md

- **Network endpoints:** http://127.0.0.1, https://api.openai.com/v1

### Review decision

- **Verdict:** Suspicious

- **Confidence:** 91.0%

- **Recommended action:** downgrade\_to\_warn

- **Intent class:** Dangerous Capability

- **False-positive risk:** Low

- **Evidence for warning:** dist/cli.js: shell tool executes arbitrary commands via exec., dist/cli.js: default App permission mode is "auto", allowing model tool calls., dist/cli.js: write\_file/edit/apply can modify files within the launch directory., dist/cli.js: main loads MCP tools and connects configured stdio/HTTP servers., dist/cli.js: interactive startup silently runs npm i -g for a newer package version.

- **Evidence against:** package.json has only prepublishOnly; no install/preinstall/postinstall hook., No hard-coded non-local exfiltration endpoint or hidden payload was found., File tools confine paths to the launch directory; sensitive writes and selected destructive shell commands are gated., Project MCP configuration requires interactive trust unless previously trusted; noninteractive mode excludes project MCP.

## Affected versions and remediation

This report applies to @guangnao/agent-cli@1.7.4.

- Review the evidence and your use of @guangnao/agent-cli@1.7.4 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.

## Public findings

### 1. Low: Non Install Lifecycle Scripts
- **Category:** Manifest
- **Confidence:** 80.0%

Package declares lifecycle scripts that are not normally run for registry tarball installs.

### 2. Low: Scripts Present
- **Category:** Manifest
- **Confidence:** 100.0%

Package declares npm scripts.

### 3. High: Child Process
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/@guangnao/agent-cli@1.7.4/dist/cli.js>)

Package source references child process execution.

Public source snippet (untrusted):

```javascript
L2879: // ../agent-llm/src/process/claude-warm.ts
L2880: import { spawn as spawn2 } from "node:child_process";
L2881: import { createInterface as createInterface2 } from "node:readline";
```

### 4. High: Shell
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/@guangnao/agent-cli@1.7.4/dist/cli.js>)

Package source references shell execution.

Public source snippet (untrusted):

```javascript
L2997: if (!needsShell(resolved)) return [resolved ?? bin, [...args], { ...opts, windowsHide: true }];
L2998: return [[resolved, ...args].map(winArg).join(" "), [], { ...opts, shell: true, windowsHide: true }];
L2999: }
```

### 5. Medium: Dynamic Require
- **Category:** Source
- **Confidence:** 75.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/@guangnao/agent-cli@1.7.4/dist/cli.js>)

Package source references dynamic require/import behavior.

Public source snippet (untrusted):

```javascript
L1539: "use strict";
L1540: var os = __require("os");
L1541: var tty = __require("tty");
```

### 6. Medium: Network
- **Category:** Source
- **Confidence:** 75.0%

Package source references network APIs.

### 7. Medium: Environment Vars
- **Category:** Source
- **Confidence:** 75.0%

Package source references environment variables.

### 8. Low: Filesystem
- **Category:** Source
- **Confidence:** 70.0%

Package source references filesystem APIs.

### 9. High: Same File Env Network Execution
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/@guangnao/agent-cli@1.7.4/dist/cli.js>)

A single source file combines environment access, network access, and code or shell execution; review context before blocking.

Public source snippet (untrusted):

```javascript
L5522: `;
L5523: var codexHome = () => process.env["CODEX_HOME"] || join9(homedir3(), ".codex");
L5524: var codexAuthPath = () => process.env["CODEX_AUTH_FILE"] || join9(codexHome(), "auth.json");
L5525: var runCli = (bin, args) => {
L5526: if (process.platform === "win32") execSync([bin, ...args].join(" "), { stdio: "inherit" });
L5527: else execFileSync2(bin, args, { stdio: "inherit" });
...
L5534: var CLIENT_ID2 = "app_EMoamEEZ73f0CkXaXp7hrann";
L5535: var TOKEN_URL = () => process.env["CODEX_TOKEN_URL"] || "https://auth.openai.com/oauth/token";
L5536: var SKEW_MS2 = 6e4;
```

### 10. High: Sandbox Evasion Gated Capability
- **Category:** Source
- **Confidence:** 84.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/@guangnao/agent-cli@1.7.4/dist/cli.js>)

Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.

Public source snippet (untrusted):

```javascript
L191: function charWidth(ch) {
L192: const cc = ch.length === 1 ? ch.charCodeAt(0) : -1;
L193: if (cc >= 32 && cc <= 126) return 1;
...
L285: GLYPH_MARKERS = /* @__PURE__ */ new Set(["\u23FA", "\u23BF", "\u2713", "\u2717", "\u25B8", "\u25CC", "\xB7", "-", "*", "!", "?", "\u25CF", "\u2514", "\xD7", "\u25BA", "\u25CB"]);
L286: legacyWin = process.platform === "win32" && !process.env["WT_SESSION"] && process.env["TERM_PROGRAM"] !== "vscode" && !/xterm|screen|vt100/i.test(process.env["TERM"] ?? "");
L287: GLYPH = {
...
L366: function terminalWidth() {
L367: return process.stdout.columns || 80;
L368: }
...
L1257: graph[models[i]] = {
L1258: // http://jsperf.com/1-vs-infinity
L1259: // micro-opt, but this is simple.
```

### 11. High: Remote Agent Bridge
- **Category:** Source
- **Confidence:** 84.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/@guangnao/agent-cli@1.7.4/dist/cli.js>)

Source exposes local file and command tools to a remote model endpoint.

Public source snippet (untrusted):

```javascript
L2879: // ../agent-llm/src/process/claude-warm.ts
L2880: import { spawn as spawn2 } from "node:child_process";
L2881: import { createInterface as createInterface2 } from "node:readline";
...
L3095: try {
L3096: const pages = Number(readFileSync(`/proc/${pid}/statm`, "utf8").split(" ")[1]);
L3097: return Number.isFinite(pages) && pages > 0 ? pages * 4096 : null;
...
L3434: claudeAutoRatio: Math.max(0, Math.floor(num(env["CLAUDE_AUTO_RATIO"], 3))),
L3435: anthropicBaseUrl: env["ANTHROPIC_BASE_URL"] ?? "",
L3436: claudeEffort: effortDefault(env["CLAUDE_EFFORT"]),
...
L4167: }
L4168: var FORCE_TOOL_LINE = "You must call one of the available tools before writing any reply.";
L4169: function claudeCliSystemPrompt(system, toolChoice, hasMcpTools) {
```

### 12. Low: Obfuscated
- **Category:** Supply Chain
- **Confidence:** 40.0%

Package source has low-confidence obfuscation-like patterns.

### 13. Low: High Entropy Strings
- **Category:** Supply Chain
- **Confidence:** 55.0%

Package source contains high-entropy string patterns.

### 14. Low: Url Strings
- **Category:** Supply Chain
- **Confidence:** 65.0%

Package source contains URL literals.

### 15. Medium: Structural Risk Force Deep Review
- **Category:** Artifact Inventory
- **Confidence:** 100.0%

Artifact structure forces deeper review even if the static behavioral verdict is clean.

## Dependencies and install lifecycle
- **Lifecycle scripts present:** Yes
- **Published lifecycle scripts:** prepublishOnly
- **Dependencies:** 0
- **Optional dependencies:** 0
- **Peer dependencies:** 0
- **Development dependencies:** 7
- **Published dependency-graph edges:** 0

## Package metadata
- **Package:** @guangnao/agent-cli
- **Ecosystem:** npm
- **Version:** 1.7.4
- **License:** MIT
- **Version published:** 2026-08-06T18:44:01.638Z
- **Package first seen:** 2026-07-01T01:51:09.243Z
- **Package last seen:** 2026-11-12T06:54:03.024Z
- **Known versions:** 31
- **Latest version:** 1.7.4
- **Appeal under review:** No
- **Description:** AgentOS terminal CLI — drive a real LLM agent on the microkernel; strongest-UX shell, advanced agent core
- **Maintainers:** guangnao
- **Keywords:** gcli, agentos, agent, llm, cli, tui, react-agent, microkernel
- **Runtime engines:** node: \>=20.12
- **Artifact files:** 3
- **Artifact unpacked size:** 779,878 bytes
- **Artifact signatures:** 1
- **Attestations:** No

## References
- [HTML security report](<https://firewall.lpm.dev/npm/@guangnao/agent-cli/v/1.7.4>)
