Skill flagged — suspicious patterns detected

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

02 Script Generator

v1.0.4

Automatically converts novel IP info into concise, platform-compliant short drama scripts with controlled pacing, conflict, and 60-second episode format.

1· 142·1 current·1 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 ghwyever/02-script-generator.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "02 Script Generator" (ghwyever/02-script-generator) from ClawHub.
Skill page: https://clawhub.ai/ghwyever/02-script-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 02-script-generator

ClawHub CLI

Package manager switcher

npx clawhub@latest install 02-script-generator
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
high confidence
Purpose & Capability
The code and SKILL.md align with the stated purpose of converting IP info to short-drama scripts via a large model. However the top-level registry metadata you provided claims "Required env vars: none" while the manifest and SKILL.md clearly require API_KEY, API_BASE, and MODEL_NAME — this mismatch is unexpected. Also source/homepage are unknown which reduces ability to verify authorship.
Instruction Scope
Runtime instructions and the implementation stay within the described task: they send the ip_info and a prompt to the configured LLM endpoint and return parsed JSON script output. The SKILL.md and code do not attempt to read other system files or unrelated environment variables. Important: the skill will transmit the full ip_info to whatever API_BASE you configure, which could leak sensitive content if ip_info contains secrets.
Install Mechanism
There is no install spec (instruction-only with a small runtime file). Nothing is downloaded from external URLs or written to unusual locations in the install step.
!
Credentials
Requesting API_KEY, API_BASE, and MODEL_NAME is reasonable for a generic LLM-backed generator, but API_BASE being user-specified allows pointing to any HTTP endpoint — meaning the skill will send your ip_info and API_KEY to that endpoint. The initial registry summary claiming no required env vars contradicts the manifest; that inconsistency should be resolved before trusting this skill.
Persistence & Privilege
The skill does not request always:true and has no special persistence or privilege. It does not modify other skills or global agent configuration.
What to consider before installing
This skill will send the ip_info you provide to the external API you configure (API_BASE) along with the API_KEY. Before installing: 1) confirm the manifest/SKILL.md requirement for API_KEY, API_BASE, and MODEL_NAME (the registry summary claiming no env vars is incorrect); 2) only use a trusted LLM provider endpoint for API_BASE — do not point it at unknown/personal servers if ip_info contains any confidential or copyrighted material; 3) be aware the code blindly parses the model's returned text as JSON (malformed responses could cause errors); 4) prefer using a provider-specific key with limited scope and rate limits; 5) because the skill's source and homepage are unknown, review or run the code in an isolated environment if possible and request provenance or an official homepage from the author. Providing any additional information (author identity, known API_BASE defaults, or an updated registry manifest) would raise confidence toward benign.

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

latestvk975hw9ns2nazc9ks1wr7vjcm584k8s4
142downloads
1stars
5versions
Updated 2w ago
v1.0.4
MIT-0

短剧剧本生成技能

功能介绍

根据IP解析结果自动生成符合抖音/番茄平台规范的短剧剧本,单集时长 90–120 秒,节奏紧凑、冲突密集。

输入参数

  • ip_info:结构化IP信息(必填)
  • episode_count:生成集数,默认 1
  • duration:单集时长,默认 90 秒,范围 90–120 秒

输出结果

  • scenes:分场景剧本列表
  • total_duration:单集总时长

使用场景

  • 小说IP自动转短剧剧本
  • 批量合规剧本生成
  • 规模化短剧内容生产

技术说明

支持通用大模型接入,需配置 API_KEY、API_BASE、MODEL_NAME。

Comments

Loading comments...