Video Cog
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: video-cog Version: 1.0.13 The video-cog skill bundle provides instructions and documentation for an AI video generation service powered by CellCog. It defines requirements for a Python environment and an API key (CELLCOG_API_KEY) and provides clear usage examples for various video production tasks. There are no indicators of data exfiltration, malicious execution, or prompt injection; the content is entirely aligned with its stated purpose of facilitating AI-driven video creation.
Findings (0)
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.
Anyone using the skill must provide a CellCog API key, which may authorize API usage and possible account billing.
The skill requires a CellCog API key. This is expected for a CellCog video-generation integration, but it is still sensitive account access.
requires:\n bins: [python3]\n env: [CELLCOG_API_KEY]
Use a dedicated or scoped CellCog API key if available, keep it out of prompts and logs, and review CellCog account limits before use.
Private scripts, marketing plans, product details, or other prompt content may be processed by CellCog and its model orchestration workflow.
The artifact directs prompts to CellCog chat/agent-team workflows. This is central to the stated video-generation purpose, but it means user-provided task content is shared with an external provider workflow.
result = client.create_chat(\n prompt="[your task prompt]",\n notify_session_key="agent:main:main",\n task_label="my-task",\n chat_mode="agent",\n) ... For video generation, always use `chat_mode="agent team"`
Avoid including confidential or regulated data unless CellCog’s data handling terms, retention, and access controls are acceptable.
The skill may rely on a separately installed CellCog component, so users should ensure they are using the intended trusted package or companion skill.
The instruction-only skill depends on an external CellCog SDK or companion dependency, but the supplied artifacts do not include package provenance or a pinned install specification. There is no evidence of automatic installation or hidden execution.
dependencies: [cellcog] ... from cellcog import CellCogClient
Install CellCog only from the official source documented by the provider and review the companion dependency before granting credentials.