← Back to Skills Marketplace
380
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install ultimate-ai-media-generator
Description
Generate AI images and videos using top-tier models including Sora 2, Kling 2.6, Seedance 2.0, Nano Banana Pro, Veo 3.1 and more. Supports text-to-image, tex...
Usage Guidance
This skill appears internally consistent: it implements a CLI that talks to CyberBara (https://cyberbara.com), requires a provider API key, saves that key under ~/.config/cyberbara/api_key, and downloads media URLs returned by the service into your media_outputs directory. Before installing: 1) only provide an API key you trust to this third-party service and verify the domain; 2) inspect the cyberbara_client gateway code (not shown in the truncated listing) if you want assurance about exact HTTP endpoints/headers it uses; 3) be aware downloaded media files will be opened automatically by default (you can disable saving/opening via flags); and 4) if you plan to run this in an automated/privileged agent, remember it will perform network calls to the provider and could consume account credits. If any of these behaviours are unacceptable, do not install or run until you audit the client implementation and verify the provider.
Capability Analysis
Type: OpenClaw Skill
Name: ultimate-ai-media-generator
Version: 1.0.1
The skill provides a functional CLI and API wrapper for the CyberBara AI media generation service. It is classified as suspicious due to the high-risk 'auto-open' functionality implemented in `src/cyberbara_cli/usecases/media_output.py`, which automatically executes system-level commands (`open`, `xdg-open`, or `cmd /c start`) on files downloaded from the remote API. While this behavior is explicitly documented in `SKILL.md` as a feature, it introduces a potential Remote Code Execution (RCE) vector if the remote service (cyberbara.com) were compromised or returned malicious payloads. Additionally, the `raw` command in `src/cyberbara_cli/cli.py` allows the agent to perform unconstrained HTTP requests to the base domain, which increases the attack surface.
Capability Assessment
Purpose & Capability
Name/description describe model-backed image/video generation. The bundle includes a CLI, prompt/workflow templates, credit-quote/polling flow, and client gateway code that targets CyberBara endpoints (base URL fixed to https://cyberbara.com). Required artifacts (API key, upload + generate + poll) align with this purpose.
Instruction Scope
SKILL.md and CLI instruct only on discovering models, quoting credits, uploading images, submitting generation tasks, polling for results, saving outputs, and persisting an API key under ~/.config/cyberbara/api_key. There are no instructions to read arbitrary system files, sweep environment variables beyond CYBERBARA_API_KEY, or exfiltrate unrelated data.
Install Mechanism
No install spec is provided (instruction-only install). The package contains Python source files which are intended to be run locally (python3 scripts/cyberbara_api.py). This is low risk in the sense that no remote installer/unknown URL downloads are configured by the skill itself.
Credentials
The only credential surface is CyberBara API key (supported via --api-key, CYBERBARA_API_KEY env var, or local cache). That matches the described need to call the provider API. No unrelated secrets or multiple external credentials are requested.
Persistence & Privilege
The skill persists only its own API key to ~/.config/cyberbara/api_key (and masks it in CLI output). It does not request 'always' inclusion and does not modify other skills or system-wide agent configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ultimate-ai-media-generator - After installation, invoke the skill by name or use
/ultimate-ai-media-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
v1.0.1 - Enhanced description to highlight top-tier AI models (Sora 2, Kling 2.6, Seedance 2.0, Nano Banana Pro, Veo 3.1). Added built-in prompt optimization for SEO articles, presentations, anime, and more use cases.
v1.0.0
Initial release – provides end-to-end automation for CyberBara API v1 media generation tasks.
- Supports model discovery, reference image upload, credit estimation, task creation, status polling, and credit balance/usage queries.
- Implements confirmation-gated image and video generation with automated credit quoting.
- Provides caching and interactive setup for API key management.
- Automatically saves and optionally opens generated media outputs.
- Includes command-line interface for direct control and enforcement of API payload rules.
Metadata
Frequently Asked Questions
What is Ultimate AI Media Generator?
Generate AI images and videos using top-tier models including Sora 2, Kling 2.6, Seedance 2.0, Nano Banana Pro, Veo 3.1 and more. Supports text-to-image, tex... It is an AI Agent Skill for Claude Code / OpenClaw, with 380 downloads so far.
How do I install Ultimate AI Media Generator?
Run "/install ultimate-ai-media-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ultimate AI Media Generator free?
Yes, Ultimate AI Media Generator is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Ultimate AI Media Generator support?
Ultimate AI Media Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Ultimate AI Media Generator?
It is built and maintained by ZeroLu (@zerolu); the current version is v1.0.1.
More Skills