Skills/ClawHub/owlwrite-paper

owlwrite-paper@1.3.1

CAUTION· static only

Publisher claims: "论文全流程工作台（夜猫子）：背靠全球 12 亿级文献资源（8000 万篇授权中文期刊，检索命中可取授权全文 PDF；外文 OA 文献免费取全文）与维普官方检测服务。文献检索、引文追溯、论文写作、科研配图（TikZ 矢量示意图 / 数据图表 / AI 科研配图）、按学校模板排版出 PDF、查重、AIGC 检测、格式检测、斟知智评评级、数据与图像可信度检测、参考文献质量检测、斟校对、引文核验与撤稿把关、余额与充值。当用户说「写论文 / 找文献 / 查文献 / 下论文 / 查这篇引用了谁 / 画流程图 / 画技术路线图 / 画示意图 / 画数据图表 / 论文配图 / 机制图 / 按学校模板排版 / 论文排版 / 格式调成学校要求 / 导出可提交的 PDF / 查重 / 测 AI 生成风险 / 查论文格式 / 论文评级 / 图有没有造假 / 参考文献对不对 / 引用有没有被撤稿 / 还剩多少点 / 校对 / 改错别字 / 帮我校对论文 / 充值 / 交钱买点数」时使用。安装后即可使用：不配置 MCP 也能直接用（可选支持 MCP 接入）。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher j-levee · publishing for 118 daysInstalls 327Last detonated 5d ago
What would fix thisWatchDispute verdict

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.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-09 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. 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
File permission modification commandscripts/owl_api.py:101 · File permission modification command — agent changes file ownership/permissionschmod 失败会在 stderr 明确告警（绝不静默）。Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)scripts/owl_api.py:6 · MCP server using network transport (SSE/HTTP) — data sent over networkMCP 服务器（mcp_server.py）是独立实现（异步 httpx，远程常驻场景不能引入同步阻塞）；Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈8,396 tok
1 file · 15 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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim j-levee: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  3. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim j-leveePropose a patch to the maintainer