pm-proto-prd-pin@2.1.0
CAUTION· install onlyPublisher claims: "为任意 HTML 原型、Vue 2/3、React 17/18/Next.js 项目植入 2.1.0 版交互式 PRD 打点标注器、多版本规约生成系统与分组管理引擎。包含亮色玻璃 UI、内联 SVG 矢量图标、圆角方标牌、三态抽屉、分组新增与元素拾取定位、拖拽调序与插入指示线、按组自动重排打点编号、管理模式统一保存与二次确认、未保存变动横条、取消打点入口、动态视图与弹窗锚点定位、定位前状态准备钩子 PRD_PREPARE_ANCHOR、分组归属接口 PRD_GROUPS_RESOLVE、顶部分组默认展开、当前视图与顶部模块过滤、四语言热切换 i18n、访客只读权限隔离、Cloudflare D" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 2026-11-13 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
kvSecretKeyPlaceholder: 'Paste your secret Master Key to unlock write permissions',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…d(t,{Y:()=>i,g:()=>r});var r="3.10.8",i=function(){function e(){}return e.ZWSP="",e.DROP_EDITOR="application/editor",e.MOBILE_WIDTH=520,e.CLASS_MENU_DISABLED="v…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…ove("vditor-panel--left")))}))},y=n(598),b=n(164),w=function(e,t,n,r){r&&console.log("".concat(e," - ").concat(n,": ").concat(t))},E=n(288),k=n(784),S=n(51),T=n(500),L=n(339),_=n(108),C=n(960),M=n(975),x=n(597),A=n(162),N=n(591),H=n(931),D…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Cost to the agent
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
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim barry0-0: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.