Kling Video

Generate AI videos with Kuaishou Kling via AceDataCloud API. Use when creating videos from text or images, extending existing videos, or applying motion cont...

Security Scan

The skill's instructions are coherent for calling AceDataCloud's Kling video API, but the manifest omits the API credential it actually requires and the SKILL.md contains parameters (callback_url) that could be misused for data exfiltration—this mismatch and potential for unsolicited callbacks merit caution.

Purpose & Capability

The skill's purpose (generate videos via AceDataCloud Kling) matches the curl examples and endpoints in SKILL.md, so capabilities align; however the published registry metadata lists no required environment variables or primary credential while the SKILL.md explicitly states 'Requires ACEDATACLOUD_API_TOKEN'. That manifest/metadata omission is an incoherence and should be fixed before trusting the skill.

Instruction Scope

SKILL.md contains concrete HTTP examples and parameter definitions limited to the stated API endpoints (POST to api.acedata.cloud). It does not instruct reading unrelated local files. Note: the documented 'callback_url' parameter can be set to arbitrary endpoints by the caller; if an agent or user supplies an attacker-controlled callback, uploaded/generated media or task results could be sent to a third-party URL.

Install Mechanism

Instruction-only skill with no install steps or downloaded code — lowest install risk.

Credentials

The runtime instructions require ACEDATACLOUD_API_TOKEN, which is proportional for API access, but the skill registry metadata did not declare this required environment variable or a primary credential. The missing declaration reduces transparency and prevents proper permission review.

Persistence & Privilege

No special persistence requested (always:false). Default autonomous invocation is allowed (platform default) but the skill does not request persistent system-wide changes or access to other skills' config.

What to consider before installing

This skill appears to be a straightforward instruction-only wrapper for AceDataCloud's Kling API, but the published metadata omits the required ACEDATACLOUD_API_TOKEN—ask the publisher to update the manifest to declare that primary credential before installing. Treat any token you provide as sensitive: use least-privilege or short-lived credentials if possible. Be cautious with the callback_url parameter: if you allow the agent to set arbitrary callback URLs, results or uploaded media could be sent to third-party endpoints. Verify the API domain (api.acedata.cloud), the skill owner identity, and any privacy/terms for uploading video content before use.

Kling Video Generation

Generate AI videos through AceDataCloud's Kuaishou Kling API.

Authentication

export ACEDATACLOUD_API_TOKEN="your-token-here"

Quick Start

curl -X POST https://api.acedata.cloud/kling/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "text2video", "prompt": "a cat playing piano on a rooftop at sunset", "model": "kling-v2-5-turbo", "mode": "std", "duration": 5}'

Models

Model	Quality	Best For
kling-v1	Standard	Basic generation, lowest cost
kling-v1-6	Improved	Better quality than v1
kling-v2-master	High	High-quality output
kling-v2-1-master	High	Improved v2
kling-v2-5-turbo	High + Fast	Best speed/quality trade-off (recommended)
kling-video-o1	Premium	Highest quality

Quality Modes

Mode	Speed	Cost	Use For
std (Standard)	Slower	Lower	Draft/preview
pro (Professional)	Faster	Higher	Final output

Workflows

1. Text-to-Video

POST /kling/videos
{
  "action": "text2video",
  "prompt": "a futuristic city with flying cars",
  "model": "kling-v2-5-turbo",
  "mode": "std",
  "duration": 5,
  "aspect_ratio": "16:9"
}

2. Image-to-Video

Animate a still image. Optionally specify an ending frame.

POST /kling/videos
{
  "action": "image2video",
  "prompt": "the scene slowly comes alive with movement",
  "start_image_url": "https://example.com/scene.jpg",
  "end_image_url": "https://example.com/end-scene.jpg",
  "model": "kling-v2-5-turbo",
  "mode": "pro"
}

3. Extend Video

Continue an existing video with additional seconds.

POST /kling/videos
{
  "action": "extend",
  "video_id": "existing-video-id",
  "prompt": "the camera pulls back to reveal the full landscape",
  "model": "kling-v2-5-turbo"
}

4. Motion Control

Apply precise camera/motion control from an image + reference video.

POST /kling/motion
{
  "image_url": "https://example.com/subject.jpg",
  "video_url": "https://example.com/motion-reference.mp4"
}

Parameters

Parameter	Values	Description
action	"text2video", "image2video", "extend"	Generation mode
model	See models table	Model to use
mode	"std", "pro"	Quality mode
duration	5, 10	Duration in seconds
aspect_ratio	"16:9", "9:16", "1:1"	Video aspect ratio
cfg_scale	0–1	Prompt relevance strength
negative_prompt	string	What to avoid in the video
camera_control	object	Camera movement parameters
callback_url	string	Async callback URL

Task Polling

POST /kling/tasks
{"task_id": "your-task-id"}

States: processing → succeed or failed.

Gotchas

• duration only supports 5 or 10 seconds
• end_image_url is only for image2video action — it defines the last frame
• Motion control (/kling/motion) is a separate endpoint from video generation
• pro mode costs roughly 2x std mode but generates faster with better quality
• Task states use "succeed" (not "succeeded") — check for this value when polling
• negative_prompt helps avoid unwanted elements (e.g., "blurry, low quality, text")