🖼️ Image to Video in Canva — Canva 图片转视频
v1.0.0使用Canva将三张产品照片或单张风景图片转换为1080p动画视频，只需输入需求即可完成转换。
0· 60·0 当前·0 累计
by 下载技能包
最后更新
2026/4/13
安全扫描
OpenClaw
可疑
medium confidenceThe skill's runtime instructions broadly match a cloud-based image→video service, but there are a few mismatches and vague behaviors ( misleading name, undeclared config path use, implicit filesystem checks ) that warrant caution before installing.
评估建议
This skill appears to call an external service (mega-api-prod.nemovideo.ai) to render videos and will upload any images you drop into the chat—so your images and metadata will leave your machine/agent. The skill name references 'Canva' but it does not use Canva APIs; that is potentially misleading. Before installing or using it, consider:
- Do you trust nemovideo.ai to receive and store your images? Check the service's privacy policy and retention practices.
- Confirm where the agent will sto...详细分析 ▾
ℹ 用途与能力
The skill claims 'in Canva' in its name but the runtime exclusively targets an unrelated service (mega-api-prod.nemovideo.ai / NEMO_TOKEN). Requiring a NEMO_TOKEN and talking to nemovideo.ai is coherent for an 'image to video' service, but the 'Canva' branding in the name is misleading and may confuse users about what platform will actually be used. Metadata also references a config path (~/.config/nemovideo/) even though registry metadata listed no required config paths—an inconsistency.
⚠ 指令范围
Instructions require the agent to upload user images and other user-provided media to an external API (expected for the stated purpose) and to create/use bearer tokens. They also instruct deriving attribution headers by detecting the agent's install path (e.g., checking for ~/.clawhub/ or ~/.cursor/skills/), which implies reading filesystem state outside the skill's payload and may be surprising to users. The doc says to 'Save session_id' but doesn't specify where—this leaves ambiguous whether tokens/session data will be persisted to disk (metadata hints at ~/.config/nemovideo/). Transmitting user images and related metadata to a third party is normal for this functionality but is an important privacy consideration and should be explicit to users.
✓ 安装机制
No install spec and no code files (instruction-only). This is the lower-risk model because nothing is written to disk by an installer, but runtime behavior still sends data to an external service.
ℹ 凭证需求
The skill requests a single credential (NEMO_TOKEN) which is proportional to calling the described API. However, metadata lists a config path (~/.config/nemovideo/) that was not declared in the registry's required config paths; the runtime also expects to be able to check install paths to derive headers. These imply potential read/write access to local config beyond the single env var and should be clarified.
✓ 持久化与权限
The skill does not request 'always: true' and uses the normal autonomous-invocation model. There is no explicit instruction to modify other skills or system-wide settings. The only persistence ambiguity is where session tokens/session_id are saved (in-memory vs a local config path), which the SKILL.md does not specify.
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 Image to Video in Canva — quickly turn images into animated videos. - Instantly convert up to 3 images into 1080p videos with no local setup required. - Drag and drop images or provide links, then describe your desired result to generate an animated video in seconds. - Includes robust session management, automatic free credit allocation, and cloud-based rendering (MP4 export, music, text overlays, and more). - Handles error cases (token expiry, file type/size limits, insufficient credits) with clear user messages and guidance. - Supports simple prompt-based editing for fast content creation and sharing.
● 无害
安装命令
点击复制官方npx clawhub@latest install image-to-video-in-canva
镜像加速npx clawhub@latest install image-to-video-in-canva --registry https://cn.longxiaskill.com 镜像可用