These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
Superagent SDK
Superagent SDK is an open-source software development kit (SDK) designed to embed runtime safety and security controls directly into AI agent applications. It provides four core capabilities:
- Guard detects and blocks prompt injections, malicious instructions, and unsafe tool invocations in real time as an AI agent operates.
- Redact automatically identifies and removes personally identifiable information (PII), protected health information (PHI), and secrets (e.g., API keys, national insurance/social security numbers) from text passing through an AI system.
- Scan analyses code repositories for AI-agent-targeted threats, such as "repo poisoning" or hidden malicious instructions aimed at coding agents.
- Test (in development) runs red-team scenarios (e.g., simulated prompt injection or data exfiltration attacks) against a production agent to surface vulnerabilities before deployment.
Auto-discovered on 2026-02-10 by OECD Catalogue Automation
About the tool
You can click on the links to see the associated tools
Tool type(s):
Objective(s):
Lifecycle stage(s):
Type of approach:
Maturity:
Usage rights:
License:
Target users:
Risk management stage(s):
Technology platforms:
Github stars:
- 6762
Github forks:
- 962
Use Cases
Would you like to submit a use case for this tool?
If you have used this tool, we would love to know more about your experience.
Add use case
Partnership on AI
