ClawHub

IMA AI Video Generator — Short & Promo Video, Text to Video, Image to Video Generation

v1.0.6

AI video generator with premier models: Wan 2.6, Kling O1/2.6, Google Veo 3.1, Sora 2 Pro, Pixverse V5.5, Hailuo 2.0/2.3, SeeDance 1.5 Pro, Vidu Q2. Video ge...

⭐ 1· 512·0 current·0 all-time
byDai Shuo@dai-shuo
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the actual code and runtime requirements: the package bundles a Python script to call IMA Studio APIs and only requires python3 and IMA_API_KEY. No unrelated credentials or binaries are requested.
ℹ
Instruction Scope
SKILL.md and SKILL-DETAIL.md explicitly instruct the agent to read the provided SKILL-DETAIL.md before first use and optionally read ima-knowledge-ai reference files if that other skill is installed. The script uploads local images to the provider and sends prompts to provider endpoints; it does not instruct reading arbitrary system files or exfiltrating unrelated data. Users should be aware that local image files will be uploaded (if provided) and that the skill may read a small set of OpenClaw paths (preferences and logs) and the ima-knowledge-ai references when present.
✓
Install Mechanism
No external download/install is declared (script-bundled). requirements.txt lists only 'requests'. There are no obscure URLs for code installation and included code is plain Python source.
✓
Credentials
Only IMA_API_KEY is required (declared as primary). The code uses that key to authenticate to two IMA-owned domains (api.imastudio.com and imapi.liveme.com) as documented in SKILL.md; this is proportionate to image upload and task creation.
ℹ
Persistence & Privilege
The skill writes preferences and logs under ~/.openclaw (ima_prefs.json and ~/.openclaw/logs/ima_skills/). always is false and the skill is user-invocable. Writing prefs/logs is reasonable for this skill type, but note logs and prefs live in the user's OpenClaw directory and the skill may read ima-knowledge-ai references if that skill is installed.
Assessment
This skill appears coherent: it uses a bundled Python script and only needs an IMA API key. Before installing, verify you trust imastudio.com because your IMA_API_KEY will be sent to api.imastudio.com (video API) and imapi.liveme.com (image upload/CDN) when you upload or use local images. Be aware that local image files provided to the skill will be uploaded to IMA's OSS/CDN. The skill stores preferences and logs under ~/.openclaw (rotate/inspect these files if you care about local traces). If you reuse credentials across services, consider creating a dedicated IMA API key with minimal permissions and be prepared to rotate it if needed. Finally, if you want extra assurance, open and review scripts/ima_video_create.py and scripts/ima_logger.py (they are plain Python) and the SKILL-DETAIL.md to confirm behaviour and endpoints before use.

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

latestvk971y3z6vgb2d0qwxbg7mxpfyx83q7e3

License

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

Runtime requirements

Binspython3
EnvIMA_API_KEY
Primary envIMA_API_KEY

Comments