← Back to Skills Marketplace
42
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install openai-image-gen-hardened
Description
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Usage Guidance
This skill appears coherent and implements what it claims: it uses your OPENAI_API_KEY to call the OpenAI Images API, saves generated images and prompts locally, and creates a local index.html gallery. Before installing: (1) Only provide an OPENAI_API_KEY with appropriate scope/permissions and monitor billing — image generation can incur costs. (2) Review and keep the key secret (the script reads it from the environment; do not embed keys in files). (3) The script downloads image URLs returned by the API (expected) — ensure you trust the environment where you run it and avoid running on systems with sensitive data if you worry about downloaded content. (4) The package source is listed as unknown; if provenance matters, verify the publisher or inspect/approve the included files (scripts/gen.py and SAFETY.md) yourself before running. (5) Brew will install python if missing; consider running in an isolated environment (container or VM) if you want to minimize side effects. Overall, the skill is internally consistent and proportionate, but protect your API key and monitor usage.
Capability Analysis
Type: OpenClaw Skill
Name: openai-image-gen-hardened
Version: 1.0.0
The skill is a legitimate tool for batch-generating images via the OpenAI API. The Python script `scripts/gen.py` implements standard API interaction, local file storage, and HTML gallery generation without any signs of data exfiltration, obfuscation, or malicious execution. The `SKILL.md` and `SAFETY.md` files contain defensive instructions (guardrails) intended to prevent the AI agent from leaking the `OPENAI_API_KEY` or accessing unauthorized directories, which aligns with the 'hardened' naming convention.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description, declared requirements (python3, OPENAI_API_KEY), SKILL.md instructions, and the included script all match: they call the OpenAI Images API, save images locally, and build an index.html gallery. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs running the included Python script and opening the local gallery. The script only reads the OPENAI_API_KEY env var, calls the OpenAI Images API, downloads returned image URLs, writes files into a timestamped local output directory, and writes prompts.json/index.html — all within the stated scope. The skill also includes explicit guardrails in SKILL.md/SAFETY.md to avoid exfiltration and key exposure.
Install Mechanism
Install spec is a single brew formula for python, which is proportionate and expected for a Python script. No downloads from untrusted URLs or archive extraction are present.
Credentials
Only OPENAI_API_KEY is required and declared as the primary credential. The script does not read other environment variables or require unrelated secrets. Requiring the OpenAI API key is appropriate for the described functionality.
Persistence & Privilege
The skill does not request always:true and will not force permanent inclusion. It does not modify other skills or system-wide configs. Its runtime activity is limited to local filesystem writes in a project-timestamped directory and outbound API/network calls to the OpenAI endpoint and any image URLs returned by that API.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openai-image-gen-hardened - After installation, invoke the skill by name or use
/openai-image-gen-hardened - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
openai-image-gen-hardened v1.0.0
- Initial release of a batch OpenAI image generation script with a prompt sampler and local HTML gallery output.
- Supports multiple OpenAI image models (dall-e-2, dall-e-3, gpt-image models) with model-specific parameters for size, quality, and format.
- Command-line interface enables custom prompts, output directories, and advanced model parameters.
- Outputs images, prompt-to-file mapping (prompts.json), and an `index.html` gallery for browsing results locally.
- Security: Enforces guardrails to prevent external uploads, restrict file access to output directory, and keep `OPENAI_API_KEY` secret in all logs and outputs.
Metadata
Frequently Asked Questions
What is Openai Image Gen Hardened?
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. It is an AI Agent Skill for Claude Code / OpenClaw, with 42 downloads so far.
How do I install Openai Image Gen Hardened?
Run "/install openai-image-gen-hardened" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openai Image Gen Hardened free?
Yes, Openai Image Gen Hardened is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Openai Image Gen Hardened support?
Openai Image Gen Hardened is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openai Image Gen Hardened?
It is built and maintained by Faberlens (@snazar-faberlens); the current version is v1.0.0.
More Skills