A powerful security and identity layer that enables agent verification, trust scoring, and real-time guardrail enforcement for AI systems.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install praesidia
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install praesidia using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Praesidia?
Praesidia is a specialized security framework designed to bring trust and safety to the AI agent ecosystem. By integrating this skill into your workflow, you can verify the identity of agents, assess their reliability through a 0-100 trust score, and implement sophisticated security policies. It acts as a shield, ensuring that every interaction with internal or third-party agents meets your specific compliance and security standards.
As part of the library of Openclaw Skills, Praesidia provides a standardized way to fetch Agent-to-Agent (A2A) protocol cards and discover marketplace agents. It empowers developers to build safer AI applications by providing deep visibility into agent capabilities, compliance statuses like GDPR or SOC2, and historical reputation data.
Praesidia Use Cases
- Verify the safety and reputation of an AI agent before delegating sensitive tasks.
- Discover public agents in the marketplace that specialize in specific roles like data analysis.
- Apply real-time guardrails to redact PII or block toxic content in agent communications.
- Enforce regulatory compliance for healthcare or financial agents using pre-built templates.
- Monitor the status and trust levels of an entire fleet of organizational agents.
How Praesidia Works
- The skill connects to the Praesidia API using a secure API key to fetch detailed identity and trust metadata.
- When an agent is queried, the system retrieves its A2A agent card containing trust scores, capabilities, and compliance records.
- For security enforcement, users can select from templates like PII detection or prompt injection prevention to apply to their agents.
- Content is validated against these guardrails in real-time, allowing the system to block, redact, or warn based on policy triggers.
- Developers can search the discovery endpoint to filter agents by role, visibility, or specific keywords to find the most trustworthy tools for their needs.
Praesidia Setup
To begin using Praesidia within the ecosystem of Openclaw Skills, follow these installation steps:
- Create an account at praesidia.ai and generate an API key from the Settings menu.
- Configure your environment by adding the skill to your local configuration file:
{
"skills": {
"entries": {
"praesidia": {
"apiKey": "pk_live_your_key_here",
"env": {
"PRAESIDIA_API_URL": "https://api.praesidia.ai"
}
}
}
}
}
- Ensure the
PRAESIDIA_API_KEYis exported in your terminal session or added to your environment variables.
Praesidia Data Schema & Taxonomy
The skill manages agent data and security policies using a structured schema to ensure clarity and interoperability.
| Property | Description | Example Value |
|---|---|---|
| Agent ID | Unique identifier for the agent | chatbot-v2 |
| Trust Score | Numerical reputation rating (0-100) | 92.5 |
| Trust Level | Categorical safety classification | VERIFIED |
| Guardrails | Array of active security policy objects | [PII_DETECTION, TOXICITY] |
| Compliance | List of certifications met by the agent | [SOC2, GDPR] |
| Capabilities | Defined functional permissions | [data:analyze, message:send] |
Praesidia Advanced Features
- Multi-layer guardrail templates covering content moderation, security, compliance, brand safety, and hallucination detection.
- Sophisticated action handling allowing for BLOCK, REDACT, WARN, or ESCALATE responses to policy violations.
- Support for different validation types including fast Rule-based matching, ML models, and high-accuracy LLM validation.
- Discovery filters to find agents by role (SERVER/CLIENT), visibility, and active status within the marketplace.
- Full A2A protocol support for standardizing agent identity across different platforms and providers.
SKILL.md
Loading
Related Openclaw Skills
Praesidia
A comprehensive security and identity layer for AI agents that enables trust verification, agent discovery, and real-time policy enforcement.
Praesidia
Praesidia is a comprehensive security and identity layer for AI agents, offering trust scoring, marketplace discovery, and automated guardrail enforcement.
OpenClaw Ticket Assistant
An intelligent assistant that automates the creation of support tickets by analyzing customer service chat screenshots.
mcporter
A powerful CLI utility for interacting with Model Context Protocol (MCP) servers, enabling direct tool calling, authentication, and code generation.
OpenClaw Smart Agent Hub
An intelligent multi-provider LLM assignment and routing system that optimizes AI agent workflows for cost, latency, and quality.
EvidenceOps: Forensic Media Triage
A professional suite of Openclaw Skills for forensic-grade media triage that ensures data integrity and a verifiable chain of custody for digital evidence.
METADATA
Featured*
