Skills/ClawHub/mu-excel-toolbox

mu-excel-toolbox@1.1.1

VERIFIED· install only

Publisher claims: "Excel全能工具箱:读写、预览、合并、拆分、关联、去重、清洗、校验、模板填充、样式、条件格式、公式、图表、透视表、数据分析、差异对比、图片插入、密码保护。典型场景:月度业务报表合并汇总、HR花名册/考勤表关联清洗、运营数据透视分析、绩效数据校验去重、批量生成offer/通知模板、薪酬表加密保护、业务周报图表生成。触发词:Excel、表格、xlsx、csv、电子表格、合并Excel、拆分Excel、Excel图表、数据透视表、Excel公式、条件格式、数据清洗、Excel模板、Excel对比、Excel加密、VLOOKUP、去重、数据校验、统计分析、格式转换、业务报表、花名册、考勤表、绩效数据、运营数据、excel toolbox、spreadsheet、merge excel、split excel、excel chart、pivot table。即使用户没有明说'用Excel工具箱',只要涉及Excel/表格/xlsx/csv文件的操作都应触发。不适用:在线协作编辑(用Google Sheets等在线工具)、纯代码开发、Skill管理。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher muippt · publishing for 79 daysInstalls 977Last detonated 7d ago
$clawhub install mu-excel-toolbox
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 90/100 (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 · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Hex-encoded string detectedscripts/utils.py:123 · Hex-encoded string detected — may contain obfuscated payloadsif header[:8] == b"\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1":Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Fake instruction boundary tagreferences/api-reference.md:238 · Fake instruction boundary tag · informational: not an instruction file · informational: not an instruction file · informational: not an instruction filepython3 validate.py <input_file> --rules <RULES> [OPTIONS]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈1,142 tok
1 file · 33 in bundle

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

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

mu-excel-toolbox@1.1.1 safety verdict: Verified (install only) — KillerSkills