ClawHub
Skill flagged — suspicious patterns detected

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

ai-drama-prompt-factory

v1.0.0

AI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包（角色立绘+场景+道具+分镜图片+视频+音频）的完整流水线。一个入口启动全流程，内部自动按阶段推进：策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原创短剧两条路径。触发词：AI短剧、短剧制作、小说转短剧、短剧提示词、提示词...

⭐ 3· 732·2 current·4 all-time
by@zhgarylu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (convert stories to structured prompt packages) align with the included references, templates, and scripts (indexing, fetching, summarizing, search). Required env/configs are none, and the package contents (style guides, assembly rules, prompt examples, JSON schemas) match the stated purpose.
✓
Instruction Scope
SKILL.md confines the agent to collecting project parameters and producing structured JSON prompt packages (phases 1–5). It references document-indexing for >30k texts and the included doc_* scripts support that. There are no instructions to read unrelated system files, access secrets, or transmit data to unexpected endpoints. The docs include example integrations (generate_image/generate_video/register_character) as consumer examples but do not contain mandatory external endpoints or credential use.
✓
Install Mechanism
No install spec is declared (instruction-only) and the code files are shipped with the skill. There are no downloads from external URLs, no brew/npm installs, and no archives to extract. The provided Python scripts operate on local files and are standard utilities for indexing/searching/summarizing documents.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The functionality (reading user-provided story text, building indexes, producing prompt JSON) legitimately needs only local file access and does not require external service tokens. The documentation mentions third‑party platforms (Midjourney, Seedance, Runway) only as optional consumers; no credentials for them are requested by the skill.
✓
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges. It contains no code that modifies other skills or global agent config. The scripts are ordinary utilities that read/write local project files (manifest, ep packages, continuity states) within the project's output directories.
Assessment
This package appears coherent for converting stories into structured prompt packages and includes helpful reference docs and Python utilities for indexing/searching long texts. Before installing or running anything: (1) review and run the included scripts in a sandbox or project directory you control — they perform local file I/O and index files you point them at; (2) do not provide unrelated system files or secrets as input; (3) if you later connect generated prompts to external generator services (Seedance, Midjourney, Runway, TTS providers), those integrations will require separate API keys — the skill does not request them by itself; (4) the skill source is listed as unknown — if provenance matters to you, prefer packages from known authors or audit the code locally before use.

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

latestvk9704dmev7ks0hvyz3vywe5t3581t63a

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments