Scene Video Generator
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill is coherent for generating AI video clips, but it may use third-party video services with API keys and may send prompts or reference images to those services.
This skill appears safe to install as an instruction-only video-generation helper. Before using it, decide which backend you trust, protect any API keys, set quota or spending limits if possible, and avoid sending sensitive images or confidential prompts to third-party video services.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If configured, the agent may be able to submit generation jobs using the user's provider account and consume credits or quota.
The skill documentation shows configuration of third-party provider credentials. This is expected for video-generation backends, but those keys can grant access to paid provider accounts.
"kling": { "access_key": "your_access_key", "secret_key": "your_secret_key" }Use provider-specific keys with the least needed permissions, set spending/quota limits where available, and avoid pasting real secrets into chat transcripts or shared documents.
Prompts, scene descriptions, and uploaded reference images may be processed by third-party AI video services.
The workflow explicitly sends optional reference images and prompts to external image-to-video or text-to-video APIs. This is purpose-aligned, but the artifacts do not specify provider retention or privacy boundaries.
上传参考图 ↓ 调用 image-to-video API ↓ 输出: 视频 URL
Do not use sensitive, private, or confidential images/prompts unless the selected provider's privacy and retention terms are acceptable.