Skills/ClawHub/cue-omni-reader

cue-omni-reader@1.2.21

CAUTION· static only

Publisher claims: "输入URL或上传文件(PDF/Office/图片/扫描件/音视频/网页/压缩包等不限定文件格式),将任意文档/文件/网页内容解析为Markdown,即插即用、默认不落盘,具有极高隐私保护。可精准还原文档目录结构和复杂表格结构,适用于高精度高性能要求的文档处理OCR任务;可将音视频内容一键解析转化为文字稿,并具备画面视觉理解能力,适用于视频转脚本、主流视频网站url提取ppt等场景。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher panting09266-ai · publishing for 28 daysInstalls 1,493Last detonated 33 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

What changed since 1.2.17

vet-skills diff cue-omni-reader 1.2.17 1.2.21

In the sandbox, this version reached for nothing 1.2.17 did not. Compared from the two recorded runs, not from source.

1.2.21 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

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 analysed it statically (a sandbox run is pending) on 2026-11-20 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Privileged sudo command. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
npx invocation of non-well-known packageSKILL.md:156 · npx invocation of non-well-known package — may execute untrusted codenpx -y @cueai/[email protected] setupFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commandSKILL.md:367 · Privileged sudo command — agent may execute with elevated privileges| PDF (.pdf) | pandoc + LaTeX | `brew install --cask basictex` | `sudo apt install texlive-xetex` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:180 · npx invocation of non-well-known package — may execute untrusted code**验证**:`npx -y @cueai/[email protected] doctor --json`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commandSKILL.md:366 · Privileged sudo command — agent may execute with elevated privileges| Word (.docx) | pandoc | `brew install pandoc` | `sudo apt install pandoc` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:255 · npx invocation of non-well-known package — may execute untrusted code| `LOCAL_BRIDGE_REQUIRED` | 本地文件需要安装 Bridge | ❌(需确认) | 提示后安装,或手动 `npx setup` |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:189 · npx invocation of non-well-known package — may execute untrusted codenpx -y @cueai/[email protected] uninstall --yes --jsonFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:186 · npx invocation of non-well-known package — may execute untrusted codenpx -y @cueai/omni-reader-mcp@latest setupFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈5,557 tok
1 file · 2 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.

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim panting09266-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim panting09266-aiPropose a patch to the maintainer