← Back to Skills Marketplace
379
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install aiml-safety
Description
Content moderation and safety checks. Instantly classify text or images as safe or unsafe using AI guardrails.
README (SKILL.md)
AIMLAPI Safety
Overview
Use "AI safety models" (Guard models) to ensure content compliance. Perfect for moderating user input or chatbot responses.
Quick start
export AIMLAPI_API_KEY="sk-..."
python scripts/check_safety.py --content "How to make a bomb"
Tasks
Check Text Safety
python scripts/check_safety.py --content "I want to learn about security" --model meta-llama/Llama-Guard-3-8B
Supported Models
meta-llama/Llama-Guard-3-8B(Default)- Other Llama-Guard variants on AIMLAPI.
Usage Guidance
This skill appears coherent for moderation: it will transmit whatever text you check to https://api.aimlapi.com using the AIMLAPI_API_KEY you provide. Before installing, confirm you trust the AIMLAPI service and are comfortable sending the types of content you will moderate (sensitive data will be sent to an external provider). Ensure your runtime has the Python 'requests' package installed (or add it to your environment). Also note the minor model-name mismatch between SKILL.md and the script — if you rely on a specific guard model, verify the exact model ID the provider exposes. If you need stricter privacy, do not send sensitive content to third-party APIs without reviewing their data retention/privacy policies.
Capability Analysis
Type: OpenClaw Skill
Name: aiml-safety
Version: 1.0.0
The skill bundle is designed for content moderation using the AIMLAPI service. The `scripts/check_safety.py` script securely retrieves the `AIMLAPI_API_KEY` from environment variables and sends user-provided content to `https://api.aimlapi.com/v1/chat/completions` for safety classification. This external network call and data transmission are explicitly aligned with the skill's stated purpose. There is no evidence of malicious intent, unauthorized data exfiltration, persistence mechanisms, or prompt injection attempts against the OpenClaw agent in `SKILL.md` or `README.md` beyond the skill's intended functionality.
Capability Assessment
Purpose & Capability
Name/description claim moderation via AIMLAPI guard models and the code calls an AIMLAPI chat completions endpoint using an AIMLAPI API key — this is proportionate and expected.
Instruction Scope
Runtime instructions tell the agent to run the included script with content and model arguments, which matches the code. Minor inconsistencies in model naming (SKILL.md mentions meta-llama/Llama-Guard-3-8B while the script defaults to meta-llama/LlamaGuard-2-8b) are present but do not expand scope. Important: the script sends the provided content to an external API, so any content checked will be transmitted off-host.
Install Mechanism
No install spec (instruction-only with an included script) — low install risk. The script imports the Python 'requests' library but the skill metadata doesn't declare this dependency; the runtime may fail if 'requests' is not installed. No downloads from unknown URLs or archive extraction are present.
Credentials
Only AIMLAPI_API_KEY is required and used by the code to authenticate to the AIMLAPI endpoint — this is appropriate for the stated purpose. No unrelated env vars, config paths, or secrets are requested.
Persistence & Privilege
The skill does not request 'always: true' and does not modify other skills or system configs. It runs on demand and holds no elevated persistence or privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install aiml-safety - After installation, invoke the skill by name or use
/aiml-safety - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of aimlapi-safety
- Instantly classify text or images as safe or unsafe using AI guardrails.
- Provides scripts for safety checks on user input or chatbot responses.
- Environment variable setup for secure API key usage.
Metadata
Frequently Asked Questions
What is AIML Сontent Moderation?
Content moderation and safety checks. Instantly classify text or images as safe or unsafe using AI guardrails. It is an AI Agent Skill for Claude Code / OpenClaw, with 379 downloads so far.
How do I install AIML Сontent Moderation?
Run "/install aiml-safety" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is AIML Сontent Moderation free?
Yes, AIML Сontent Moderation is completely free (open-source). You can download, install and use it at no cost.
Which platforms does AIML Сontent Moderation support?
AIML Сontent Moderation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created AIML Сontent Moderation?
It is built and maintained by AI/ML API (@aimlapihello); the current version is v1.0.0.
More Skills