Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

ppt-generator

v1.0.0

将用户讲稿一键生成乔布斯风极简科技感竖屏HTML演示稿。当用户需要生成PPT、演示文稿、Slides、幻灯片,或要求科技风/极简风/乔布斯风格的演示时触发此技能。输出为单个可直接运行的HTML文件。

0· 116·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for kirkraman/jx-ppt-generator.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "ppt-generator" (kirkraman/jx-ppt-generator) from ClawHub.
Skill page: https://clawhub.ai/kirkraman/jx-ppt-generator
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install jx-ppt-generator

ClawHub CLI

Package manager switcher

npx clawhub@latest install jx-ppt-generator
Security Scan
Capability signals
CryptoRequires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description, templates, and instructions all aim to generate a single-file HTML 'Jobs-style' vertical presentation — coherent with purpose. However, registry metadata at the top of the package claims no required environment variables while SKILL.md and agent configs declare a required SKILLBOSS_API_KEY; this mismatch is an inconsistency that should be resolved.
Instruction Scope
SKILL.md steps are limited to reading the user's provided manuscript, using an LLM to produce a refined script and titles, planning slide structure, filling the provided HTML template, and outputting the Markdown, outline, and final HTML in that order. It does not instruct the agent to read unrelated system files or to exfiltrate arbitrary data.
Install Mechanism
No install spec or code execution/install steps are present; the package is instruction + static assets only, which minimizes on-disk risk.
Credentials
The only credential referenced in SKILL.md and agent manifests is SKILLBOSS_API_KEY, which is appropriate for calling the declared LLM gateway. Concerns: (1) the top-level metadata states no required env vars (contradiction); (2) SKILL.md shows a sample call to https://api.skillbossai.com/v1/pilot while agent YAML files point to https://api.heybossai.com — inconsistent endpoints for the same credential. These mismatches should be clarified before supplying credentials.
Persistence & Privilege
always:false and no install behavior; the skill does not request permanent platform presence or modify other skills/config. The skill can be invoked autonomously by agents (default behavior) but this is normal and not by itself a red flag.
What to consider before installing
This skill appears to do what it says (produce a single HTML slide deck) but you should verify a few things before installing or providing secrets: - Resolve the metadata contradictions: the registry summary says no env vars, but SKILL.md and agent configs require SKILLBOSS_API_KEY. Don't supply your API key until you confirm which service and endpoint will actually be used. - Confirm the LLM provider domain/operator (SKILLBOSS vs heybossai vs skillbossai) and check the provider's reputation and billing/usage policies. If possible, create a scoped API key with limited permissions and low quota for testing. - The generated HTML/template loads resources (Tailwind, fonts) from third-party CDNs (bytecdntp, fonts.loli.net, etc.). Opening the final HTML will cause your browser to fetch assets from those domains, which can reveal your IP and referer and could change appearance if those resources are modified. Consider replacing CDN links with trusted CDNs or bundling local assets if privacy is a concern. - Because this is an instruction-only skill, there is no install-time filesystem risk, but the skill will call an external LLM to rewrite user content — avoid sending highly sensitive text to an external API. If you want to reduce risk: test with non-sensitive content and a test API key, or adapt the skill to use a local or organizational LLM endpoint you control.

Like a lobster shell, security has layers — review code before you run it.

aivk97c1c3j77dqm5144jmvkzw2yd856bf5latestvk97c1c3j77dqm5144jmvkzw2yd856bf5
116downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

PPT Generator

将讲稿转换为乔布斯风极简科技感竖屏HTML演示稿。

设计哲学

  • 极简主义 - 一屏只讲一件事
  • 强视觉对比 - 深色背景 + 白色文字
  • 高留白 - 禁止密集排版
  • 强节奏感 - 让观众想继续看

生成流程(必须严格遵循)

Step 1: 读取讲稿

读取用户原始讲稿,不修改原稿内容。

Step 2: 生成提炼版讲稿

将内容精简、增强冲击力、适配演示场景,输出 Markdown 格式。

Step 3: 生成乔布斯风标题

为每个章节生成标题,必须满足:

  • ≤12 字
  • 采用以下形式之一:对比式、问题式、断言式、数字式、比喻式
  • 自检:是否让人想继续听?

Step 4: 设计幻灯片结构

规划页面顺序和类型,参考 references/slide-types.md

Step 5: 生成HTML

使用 assets/template.html 作为基础模板生成完整HTML。

Step 6: 填充内容

添加动态背景光斑、交互逻辑、平滑切换动画。

输出顺序(必须依次输出)

  1. 提炼后的讲稿(Markdown)
  2. 幻灯片结构大纲
  3. 完整HTML代码

视觉规范速查

项目规范
比例9:16 竖屏
背景#000000 或 #0a0a0a + 模糊光斑动画
主文字#ffffff
辅助文字#9ca3af
中文字体HarmonyOS Sans SC / 思源黑体
英文字体Inter / Roboto
标题字重font-black / font-bold
正文字重font-light / font-normal

详细规范见 references/design-spec.md

交互要求

  • 键盘 ← → 翻页
  • 底部进度导航条
  • 平滑切换动画

技术栈

  • TailwindCSS(国内CDN)
  • 复杂页面使用 Vue3(CDN)
  • 单个HTML文件,可直接打开运行
  • LLM 内容理解与生成:SkillBoss API Hub(/v1/pilot 自动路由,type: chat

环境变量

变量说明
SKILLBOSS_API_KEYSkillBoss API Hub 认证密钥,用于调用 LLM 生成能力
requires.env: [SKILLBOSS_API_KEY]

调用示例(Step 2/3 提炼讲稿与生成标题时,宿主 agent 通过以下方式调用 LLM):

import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

response = requests.post(
    "https://api.skillbossai.com/v1/pilot",
    headers={
        "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
        "Content-Type": "application/json"
    },
    json={
        "type": "chat",
        "inputs": {
            "messages": [{"role": "user", "content": "请根据以下讲稿生成PPT大纲..."}]
        },
        "prefer": "balanced"
    }
)
text = response.json()["result"]["choices"][0]["message"]["content"]

严禁行为

  • 堆字 / 密集排版
  • 花哨配色
  • 复杂图表
  • 横屏比例
  • 偏离极简科技风

默认规则

  • 未指定页数:自动生成 8~20 页
  • 未指定风格:默认乔布斯风

Comments

Loading comments...