Text To Video Llm — 技能工具
v1.0.0generate text prompts into AI generated videos with this skill. Works with TXT, DOCX, PDF, plain text files up to 500MB. marketers, content creators, develop...
0· 35·0 当前·0 累计
by 安全扫描
OpenClaw
可疑
medium confidenceThe skill's stated purpose (convert text to video) aligns with the single required credential (NEMO_TOKEN), but the runtime instructions ask the agent to auto-create and persist auth tokens, read install paths for attribution, and hide token values — behaviors that are plausible for the service but raise scope and transparency concerns.
评估建议
Before installing, consider that this skill will: automatically contact https://mega-api-prod.nemovideo.ai and may create and store an anonymous auth token and session ID (SKILL.md suggests ~/.config/nemovideo/), perform uploads of user files to that backend, and read local install paths to set attribution headers. If you care about transparency or auditability, prefer to: (1) supply your own NEMO_TOKEN from an account you control rather than allowing automatic anonymous-token creation; (2) conf...详细分析 ▾
ℹ 用途与能力
Name/description and the declared primary credential (NEMO_TOKEN) are consistent with a cloud video-generation backend. However, the skill's YAML frontmatter (in SKILL.md) declares a config path (~/.config/nemovideo/) which is not listed in the registry 'required config paths' field — an internal inconsistency. Requiring NEMO_TOKEN is proportionate to the service's purpose.
⚠ 指令范围
The SKILL.md directs the agent to automatically contact an external API on first use, generate an anonymous token (POST to mega-api-prod.nemovideo.ai), store that token/session, and avoid showing raw API responses or token values to the user. It also instructs the agent to inspect local install paths to set an attribution header. Those steps (automatic network calls on open, persisting tokens to disk, and hiding tokens) expand the skill's runtime scope beyond a simple request/response helper and reduce transparency to the user.
✓ 安装机制
Instruction-only skill with no install spec or code files — minimal surface for arbitrary code execution. This is the lowest-risk install model.
ℹ 凭证需求
Only one environment credential (NEMO_TOKEN) is declared, which is appropriate for an API-backed video service. However, instructions imply persistent storage of tokens/sessions (and use of a config path in SKILL.md) and reading of install paths for attribution headers; those actions imply file writes/reads beyond simply using an existing environment variable.
ℹ 持久化与权限
The skill does not request always:true and is user-invocable (normal). It instructs the agent to create and persist an anonymous token and session_id (likely under ~/.config/nemovideo/ per SKILL.md frontmatter). Persisting auth data is reasonable for usability but increases persistent presence and requires the user to trust the remote service and how tokens are stored.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/13
Initial release of text-to-video-llm skill. - Generate AI-powered videos from text prompts using TXT, DOCX, PDF, or plain text files (up to 500MB). - Automated setup and authentication, with 100 free credits for new users. - Supports export of 1080p MP4 videos after 1–3 minutes of cloud GPU processing. - Seamless user interactions covering upload, status, credits, and export actions. - Cloud render pipeline handles compositing, compression, and media output with clear error handling and feedback.
● 无害
安装命令
点击复制官方npx clawhub@latest install text-to-video-llm
镜像加速npx clawhub@latest install text-to-video-llm --registry https://cn.longxiaskill.com 镜像可用