---
canonical: "https://firewall.lpm.dev/npm/xuanzhu/v/0.9.0"
markdown: "https://firewall.lpm.dev/npm/xuanzhu/v/0.9.0.md"
package: "xuanzhu"
report_status: "published"
title: "xuanzhu@0.9.0 npm security report"
verdict: "suspicious"
version: "0.9.0"
---

# xuanzhu@0.9.0 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:** 0.9.0
- **Selected version is latest:** No
- **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.

The package is an AI coding agent with a shell tool, but it enables auto-approval by default and bypasses that tool’s confirmation gate in auto mode. This is a dangerous capability that merits a warning; the reviewed source did not establish credential theft or another malicious attack.

## Latest scan
- **Scanner version:** rust-scanner-worker-schema-1
- **Recorded final verdict:** Suspicious
- **Recorded analysis confidence:** 93.0%
- **Started:** 2026-11-04T12:59:09.054Z
- **Finished:** 2026-11-04T13:01:07.357Z
- **Download time:** 510 ms
- **Static scan time:** 2123 ms
- **AI review time:** 115667 ms
- **Total time:** 118303 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:** Default auto-approval lets the agent run dangerous shell commands without asking for confirmation.

- **Trigger:** Starting the CLI with its default configuration and prompting the agent to use a tool.

- **Impact:** An agent-selected command can modify files, install software, or access environment values without a per-command confirmation.

- **Evidence paths:** dist/cli.js

- **Review source:** ai\_review

- **Reviewed:** 2026-11-04T13:01:07.357Z

### AI review details

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

- **Mechanism:** The default config enables auto-approval; in auto mode, the confirmation gate for dangerous tools is bypassed, and the bash tool executes commands in a shell with the process environment.

- **Rationale:** The package is an AI coding agent with a shell tool, but it enables auto-approval by default and bypasses that tool’s confirmation gate in auto mode. This is a dangerous capability that merits a warning; the reviewed source did not establish credential theft or another malicious attack.

- **Network endpoints:** d.officecli.ai, api.openai.com, api.deepseek.com, api.binance.com, fapi.binance.com

### Review decision

- **Verdict:** Suspicious

- **Confidence:** 93.0%

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

- **Intent class:** Dangerous Capability

- **False-positive risk:** Medium

- **Evidence for warning:** The CLI defaults autoApprove to true and maps that setting to auto mode unless autonomy is explicitly configured., In auto mode, the confirmation check for tools marked requiresConfirmation is skipped unless the mode is ask., The bash tool runs shell commands and is marked as requiring confirmation and dangerous; the command runner starts the shell with the process environment.

- **Evidence against:** Shell execution is a core feature of this AI coding agent., The reviewed source did not show credentials being sent to an unrelated host.

## Affected versions and remediation

This report applies to xuanzhu@0.9.0.

- Review the evidence and your use of xuanzhu@0.9.0 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/xuanzhu@0.9.0/dist/cli.js>)

Package source references child process execution.

Public source snippet (untrusted):

```javascript
L124: `);return;case"/status":s(this.status());return;case"/devices":s({devices:this.listDevices()});return;case"/logs":{let o=Number(n.searchParams.get("limit")??"50");s({logs:this.rece...
L125: `);return}}}};function Wu(t,e){let r=t.replace(/\s+/g," ").trim();return r.length>e?`${r.slice(0,e)}\u2026`:r}function Pm(t){return t?t.name||t.id:"\u672A\u63E1\u624B\u8FDE\u63A5"}...
L126: `).slice(1).map(r=>r.trim()).filter(r=>r.endsWith("	device"));if(e.length>0){let r=(0,Gm.execFileSync)("adb",["shell","getprop","ro.product.cpu.abi"],{timeout:5e3,encoding:"utf8",s...
```

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

Package source references network APIs.

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

Package source references environment variables.

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

Package source references filesystem APIs.

### 7. High: Same File Env Network Execution
- **Category:** Source
- **Confidence:** 85.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/xuanzhu@0.9.0/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
L115: 
L116: [\u56FE\u7247\u5DF2\u7701\u7565\uFF1A${n}\uFF08\u5F53\u524D\u6A21\u578B\u4E0D\u652F\u6301\u56FE\u7247\u8F93\u5165\uFF09]`,images:void 0}})}function Lu(t){let e=0;for(;e<t.length;){...
L117: `)}var sR=2*1024*1024,gi=class{port;baseDir;logBufferSize;options;sessions=new Set;logs=[];httpServer=null;wss=null;autojs6=null;autojs6Server=null;latestShot=null;constructor(e={}...
...
L124: `);return;case"/status":s(this.status());return;case"/devices":s({devices:this.listDevices()});return;case"/logs":{let o=Number(n.searchParams.get("limit")??"50");s({logs:this.rece...
L125: `);return}}}};function Wu(t,e){let r=t.replace(/\s+/g," ").trim();return r.length>e?`${r.slice(0,e)}\u2026`:r}function Pm(t){return t?t.name||t.id:"\u672A\u63E1\u624B\u8FDE\u63A5"}...
L126: `).slice(1).map(r=>r.tr
```

### 8. High: Credential Redirect Persistence
- **Category:** Source
- **Confidence:** 94.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/xuanzhu@0.9.0/dist/cli.js>)

Manifest-reachable source sends a prompted API credential to a fixed unofficial gateway and persists the redirection.

Public source snippet (untrusted):

```javascript
Manifest-reachable source captures an API credential, sends it to a fixed unofficial gateway, and persists that redirection in agent or shell configuration.
dist/cli.js:
"use strict";var PT=Object.create;var xC=Object.defineProperty;var _T=Object.getOwnPropertyDescriptor;var OT=Object.getOwnPropertyNames;var GT=Object.getPrototypeOf,HT=Object.proto...
`)||t.includes("\r")||t.includes("\0"))===!1}function ZL(t,e){let{headersList:r}=e,n=(r.get("referrer-policy",!0)??"").split(","),s="";if(n.length>0)for(let o=n.length;o!==0;o--){l...
`,"latin1"),r!==null&&s!==r){if(n[Kh])throw new Os;process.emitWarning(new Os)}e[me].timeout&&e[me].timeoutType===Zi&&e[me].timeout.refresh&&e[me].timeout.refresh(),n[$n]()}}destro...
`,this[F1]=c??3e5,this[N1]=s??3e5,this[L1]=C??!0,this[U1]=I,this[df]=B,this[zn
```

### 9. High: Command Output Exfiltration
- **Category:** Source
- **Confidence:** 82.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/xuanzhu@0.9.0/dist/cli.js>)

Source combines command execution, command-output handling, and outbound requests; review data flow before blocking.

Public source snippet (untrusted):

```javascript
L115: 
L116: [\u56FE\u7247\u5DF2\u7701\u7565\uFF1A${n}\uFF08\u5F53\u524D\u6A21\u578B\u4E0D\u652F\u6301\u56FE\u7247\u8F93\u5165\uFF09]`,images:void 0}})}function Lu(t){let e=0;for(;e<t.length;){...
L117: `)}var sR=2*1024*1024,gi=class{port;baseDir;logBufferSize;options;sessions=new Set;logs=[];httpServer=null;wss=null;autojs6=null;autojs6Server=null;latestShot=null;constructor(e={}...
...
L124: `);return;case"/status":s(this.status());return;case"/devices":s({devices:this.listDevices()});return;case"/logs":{let o=Number(n.searchParams.get("limit")??"50");s({logs:this.rece...
L125: `);return}}}};function Wu(t,e){let r=t.replace(/\s+/g," ").trim();return r.length>e?`${r.slice(0,e)}\u2026`:r}function Pm(t){return t?t.name||t.id:"\u672A\u63E1\u624B\u8FDE\u63A5"}...
L126: `).slice(1).map(r=>r.tr
```

### 10. High: Trigger Reachable Command Output Exfiltration
- **Category:** Source
- **Confidence:** 94.0%
- **Path:** dist/cli.js
- **Public source:** [View source](<https://unpkg.com/xuanzhu@0.9.0/dist/cli.js>)

A manifest entrypoint or package-local install chain reaches command-output exfiltration behavior.

Public source snippet (untrusted):

```javascript
Trigger-reachable command-output exfiltration chain: manifest.main -> dist/cli.js
L115: 
L116: [\u56FE\u7247\u5DF2\u7701\u7565\uFF1A${n}\uFF08\u5F53\u524D\u6A21\u578B\u4E0D\u652F\u6301\u56FE\u7247\u8F93\u5165\uFF09]`,images:void 0}})}function Lu(t){let e=0;for(;e<t.length;){...
L117: `)}var sR=2*1024*1024,gi=class{port;baseDir;logBufferSize;options;sessions=new Set;logs=[];httpServer=null;wss=null;autojs6=null;autojs6Server=null;latestShot=null;constructor(e={}...
...
L124: `);return;case"/status":s(this.status());return;case"/devices":s({devices:this.listDevices()});return;case"/logs":{let o=Number(n.searchParams.get("limit")??"50");s({logs:this.rece...
L125: `);return}}}};function Wu(t,e){let r=t.replace(/\s+/g," ").trim();return r.length>e?`${r.slice(0,e)}\u2026`:r}function Pm(t){return
```

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

Package source contains high-entropy string patterns.

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

Package source contains URL literals.

### 13. Medium: Ships Build Helper
- **Category:** Artifact Inventory
- **Confidence:** 70.0%
- **Path:** dist/assets/btc/runner.py
- **Public source:** [View source](<https://unpkg.com/xuanzhu@0.9.0/dist/assets/btc/runner.py>)

Package ships non-JavaScript build or shell helper files.

Public source snippet (untrusted):

```python
path = dist/assets/btc/runner.py
kind = build_helper
sizeBytes = 9677
magicHex = [redacted]
```

### 14. Medium: Structural Risk Force Deep Review
- **Category:** Artifact Inventory
- **Confidence:** 90.0%

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

## Dependencies and install lifecycle
- **Lifecycle scripts present:** Yes
- **Published lifecycle scripts:** prepare
- **Dependencies:** 6
- **Optional dependencies:** 0
- **Peer dependencies:** 0
- **Development dependencies:** 5
- **Published dependency-graph edges:** 6

### Published dependency entries
- @anthropic-ai/sdk ^0.52.0 (Dependency)
- @google/generative-ai ^0.21.0 (Dependency)
- openai ^4.28.0 (Dependency)
- socks ^2.8.10 (Dependency)
- undici ^6.29.1 (Dependency)
- ws ^8.22.0 (Dependency)

## Package metadata
- **Package:** xuanzhu
- **Ecosystem:** npm
- **Version:** 0.9.0
- **License:** MIT
- **Version published:** 2026-11-04T12:54:48.788Z
- **Package first seen:** 2026-10-07T19:25:10.149Z
- **Package last seen:** 2026-11-22T06:59:03.902Z
- **Known versions:** 50
- **Latest version:** 0.18.1
- **Appeal under review:** No
- **Description:** 玄猪（XuanZhu）— 专为终端打造的 AI 编码 Agent
- **Author:** amble311
- **Maintainers:** amble311
- **Keywords:** ai, agent, cli, tui, coding-assistant, llm, terminal
- **Runtime engines:** node: \>=18.0.0
- **Artifact files:** 63
- **Artifact unpacked size:** 1,636,268 bytes
- **Artifact signatures:** 2
- **Attestations:** No

## References
- [HTML security report](<https://firewall.lpm.dev/npm/xuanzhu/v/0.9.0>)
- [Repository](<https://github.com/amble311/xuanzhu>)
- [Homepage](<https://github.com/amble311/xuanzhu#readme>)
- [Issues](<https://github.com/amble311/xuanzhu/issues>)
