← Back to Skills Marketplace
12104
Downloads
0
Stars
6
Active Installs
1
Versions
Install in OpenClaw
/install ai-act-risk-check
Description
Assesses AI system risk polarity based on Annex III of the EU AI Act, identifying high-risk categories like biometrics and employment.
Usage Guidance
Install only if you are comfortable using the Gemini CLI for this check. Treat the AI-system description you type as data that may leave your local environment, and remove confidential business, personal, legal, or regulated details unless your Gemini account and data terms are appropriate for that use.
Capability Analysis
Type: OpenClaw Skill
Name: ai-act-risk-check
Version: 1.0.0
The skill executes an external command (`gemini`) via `script.sh` to perform LLM inference. While this shell access is plausibly needed for the skill's stated purpose of AI Act risk classification, it represents a high-risk capability that prevents it from being classified as benign. There is no evidence of intentional malicious behavior such as data exfiltration, persistence, or prompt injection against the agent, but the direct execution of external binaries warrants a 'suspicious' classification.
Capability Assessment
Purpose & Capability
The artifacts consistently implement a preliminary EU AI Act Annex III classifier that returns HIGH-RISK or LOW-RISK for a user-provided AI-system description.
Instruction Scope
Runtime behavior is limited to one command argument, prompt construction, a Gemini CLI inference call, and printing the result; there is no broad file access or unrelated instruction set.
Install Mechanism
The package exposes an exec script, which is expected for a command-line skill, but the documentation says no dependencies and mentions oracle while the script actually calls gemini from PATH.
Credentials
Using an external LLM is proportionate to the stated classification task and partly disclosed, but provider-specific data-transfer and privacy implications are not clearly explained to the user.
Persistence & Privilege
No artifact evidence shows persistence, background execution, privilege escalation, credential harvesting, destructive actions, local file writes, or unrelated data collection.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ai-act-risk-check - After installation, invoke the skill by name or use
/ai-act-risk-check - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of ai-act-risk-check.
- Provides a quick risk classification for AI systems per Annex III of the EU AI Act.
- Outputs HIGH-RISK or LOW-RISK with applicable high-risk category.
- No dependencies; uses only shell scripts and LLM inference.
Metadata
Frequently Asked Questions
What is Ai Act Risk Check?
Assesses AI system risk polarity based on Annex III of the EU AI Act, identifying high-risk categories like biometrics and employment. It is an AI Agent Skill for Claude Code / OpenClaw, with 12104 downloads so far.
How do I install Ai Act Risk Check?
Run "/install ai-act-risk-check" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ai Act Risk Check free?
Yes, Ai Act Risk Check is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Ai Act Risk Check support?
Ai Act Risk Check is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Ai Act Risk Check?
It is built and maintained by Bluesbell (@bluesbell); the current version is v1.0.0.
More Skills