Skills/ClawHub/openapi-lark

openapi-lark@0.1.0

CAUTION· static only

Publisher claims: "把项目 OpenAPI / Swagger spec（本地 yaml/json **或 http(s):// URL**）同步到飞书 / Lark wiki & docx 文档树。支持 single / tree / endpoint（每接口一个 wiki 子节点）三种结构，自动按 tag 拆分 + path-p..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher leeguooooo · publishing for 137 daysInstalls 385Last detonated 2d 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 2026-11-12 and scored it 66/100 (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

LOW
Instructs the agent to modify its persistent memory or instruction filesskill-card.md:52 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…ut Parameters:** [1D] **Other Properties Related to Output:** [May generate or update project configuration, CLAUDE.md guidance blocks, local OpenAPI snapshots, cache/lock files, and Feishu/Lark wik…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:19 · npx invocation of non-well-known package — may execute untrusted code之后所有命令走 `npx -y -p github:leeguooooo/openapi-lark openapi-lark <cmd>`，本 skill 已在调用前缀里嵌好。Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:16 · npx invocation of non-well-known package — may execute untrusted codenpx skills add leeguooooo/openapi-larkFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Dense URL-encoded contentSKILL.md:268 · Dense URL-encoded content — may be obfuscating payloads**GitHub Actions / Jenkins 完整范本**：见 [README 的「团队 / CI 同步」节](https://github.com/leeguooooo/openapi-lark#-%E5%9B%A2%E9%98%9F--ci-%E5%90%8C%E6%AD%A5%E6%8E%A8%E8%8D%90%E5%A7%BF%E5%8A%BF)。Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:22 · npx invocation of non-well-known package — may execute untrusted code- lark-cli 已安装：`npx @larksuite/cli@latest install`（官方唯一推荐方式；详见 [larksuite/cli](https://github.com/larksuite/cli)）+ `lark-cli auth login --recommend`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesskill-card.md:29 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileRisk: Initialization can write persistent agent instructions into CLAUDE.md by default.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:86 · npx invocation of non-well-known package — may execute untrusted codenpx -y -p github:leeguooooo/openapi-lark openapi-lark init \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈4,675 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

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim leeguooooo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Dense URL-encoded content≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim leeguoooooPropose a patch to the maintainer