Skills/npm/lanhu-design

lanhu-design@1.5.2

VERIFIED· install only

Publisher claims: "蓝湖设计稿读取、规格提取与切图下载 CLI(支持私有部署,可自定义 host)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher imaegoo · publishing for 27 daysInstalls 591Last detonated 16 min ago
$claude mcp add lanhu-design -- npx -y @imaegoo/lanhu-design
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 8 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 1.5.1

vet-skills diff lanhu-design 1.5.1 1.5.2

This version reaches for something 1.5.1 did not: 1 new host (lanhuapp.com). Compared from the two recorded runs, not from source.

New hosts
lanhuapp.com

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: node scripts/download_design_images.mjs "https://lanhuapp.com/..." --designs "首页设计" --output ./designs
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: Download Lanhu design slices from lanhu_get_design_slices JSON output.
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: node scripts/get_design_slices.mjs "https://lanhuapp.com/..." --design "首页" --no-metadata
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 2: node scripts/get_design_specs.mjs "https://lanhuapp.com/..." --design 1 --output ./tmp/specs --download-images
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 2: 示例: node scripts/get_designs.mjs "https://lanhuapp.com/web/#/item/project/stage?tid=xxx&pid=xxx"
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.8sprocess8 of 8 bundled scripts run with no arguments
0.8sprocessscript backend runs setup only
0.8sprocessscript backend runs setup only
0.8sprocessno install scripts to re-run

Static findings

MEDIUM
Unicode escape sequence detecteddist/cli.js:129 · Unicode escape sequence detected — may contain obfuscated payloadsthrow new LanhuError("LANHU_INVALID_ARGUMENT", "Cookie \u4E0D\u5F97\u5305\u542B\u6362\u884C\u7B26\u3002");Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/cli.js:16 · Unicode escape sequence detected — may contain obfuscated payloads…efault = { name: "@imaegoo/lanhu-design", version: "1.5.2", description: "\u84DD\u6E56\u8BBE\u8BA1\u7A3F\u8BFB\u53D6\u3001\u89C4\u683C\u63D0\u53D6\u4E0E\u5207\u56FE\u4E0B\u8F7D CLI\uFF08\u652F\u6301\u79C1\u6709\u90E8\u7F72\uFF0C\u53EF\u81E…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/cli.js:126 · Unicode escape sequence detected — may contain obfuscated payloadsthrow new LanhuError("LANHU_INVALID_ARGUMENT", "Cookie \u683C\u5F0F\u65E0\u6548\uFF0C\u5E94\u4E3A name=value; name2=value2\u3002");Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File permission modification commanddist/cli.js:229 · File permission modification command — agent changes file ownership/permissionsimport { chmod as chmod2, mkdir as mkdir2, readFile as readFile2, rename as rename2, rm, writeFile as writeFile2 } from "fs/promises";Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Unicode escape sequence detecteddist/cli.js:203 · Unicode escape sequence detected — may contain obfuscated payloadsthrow new LanhuError("LANHU_INVALID_ARGUMENT", "\u84DD\u6E56 host \u4E0D\u80FD\u5305\u542B\u8D26\u53F7\u5BC6\u7801\u3002");Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionskills/lanhu-design/SKILL.md:140 · File type combined with upload action — agent may exfiltrate local data filesnode scripts/download_slices.mjs slices.json --output ./src/assets/images/slices/home --scale 2xFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,072 tok
1 file · 19 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.