ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified utilities Safety 5/5

Praesidia

Verify AI agents, check trust scores (0-100), fetch A2A agent cards, discover marketplace agents, apply guardrails for security and compliance. Use when user mentions agent verification, trust scores, agent discovery, A2A protocol, agent identity, agent marketplace, guardrails, security policies, content moderation, or asks "is this agent safe?" or "find agents that can [task]" or "apply guardrails to protect my agent".

Why use this skill?

Secure your AI agents with Praesidia. Verify identities, check trust scores, and apply enterprise-grade security guardrails within OpenClaw.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/msoica/skills-a2a
Or

What This Skill Does

Praesidia is a mission-critical security and identity layer for the OpenClaw agent ecosystem. It serves as the primary bridge for establishing trust between autonomous agents, ensuring that every interaction within your workflow is verified, compliant, and protected by robust guardrails. By integrating Praesidia, users can perform real-time verification of AI identities, fetch A2A (Agent-to-Agent) protocol cards, and monitor trust scores on a scale of 0 to 100. Furthermore, the skill enables developers and power users to enforce granular security policies, such as PII redaction and toxicity filtering, ensuring that agentic outputs meet strict corporate compliance standards like SOC2 and GDPR.

Installation

To integrate Praesidia into your OpenClaw environment, first ensure you have a registered account at https://praesidia.ai and possess a valid API key. Navigate to your local configuration file located at ~/.openclaw/openclaw.json and add the Praesidia configuration block:

{
  "skills": {
    "entries": {
      "praesidia": {
        "apiKey": "your_api_key_here",
        "env": {
          "PRAESIDIA_API_URL": "https://api.praesidia.ai"
        }
      }
    }
  }
}

After updating the file, restart your OpenClaw agent instance to initialize the skill.

Use Cases

  • Zero-Trust Agent Verification: Validate the legitimacy of unknown agents before granting them access to internal data or tool execution.
  • Security Compliance Management: Automate the enforcement of guardrails (PII redaction, toxic language filtering) on agent inputs and outputs.
  • Marketplace Discovery: Search for verified, high-trust agents to assist with specific tasks such as data analysis or customer support.
  • Agent Governance: Monitor the 'Trigger Count' of security policies to identify potential attack vectors or vulnerabilities in existing agent workflows.

Example Prompts

  1. "Is the 'finance-bot-v4' agent verified and safe to connect to my data?"
  2. "Show me all active security policies and guardrails configured for my customer-support-agent."
  3. "Find me a marketplace agent that specializes in data analysis and has a trust score above 90."

Tips & Limitations

  • Always Check Trust Scores: A trust score below 70 should prompt a manual review of the agent's capabilities before deployment.
  • Scope Matters: When configuring guardrails, differentiate between 'INPUT' and 'OUTPUT' scopes to prevent sensitive data leakage while maintaining conversational flow.
  • Environment Sync: If you are developing locally, ensure the API URL is set to http://localhost:3000 to avoid hitting production endpoints with test data.
  • Rate Limiting: Be aware that frequent metadata fetching may be subject to API rate limits; use caching where possible.

Metadata

Author@msoica
Stars1335
Views1
Updated2026-02-23
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-msoica-skills-a2a": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#security#verification#compliance#trust#identity
Safety Score: 5/5

Flags: network-access, external-api

Related Skills

Praesidia

Verify AI agents, check trust scores (0-100), fetch A2A agent cards, discover marketplace agents, apply guardrails for security and compliance. Use when user mentions agent verification, trust scores, agent discovery, A2A protocol, agent identity, agent marketplace, guardrails, security policies, content moderation, or asks "is this agent safe?" or "find agents that can [task]" or "apply guardrails to protect my agent".

msoica 1335

Praesidia

Verify AI agents, check trust scores (0-100), fetch A2A agent cards, discover marketplace agents, apply guardrails for security and compliance. Use when user mentions agent verification, trust scores, agent discovery, A2A protocol, agent identity, agent marketplace, guardrails, security policies, content moderation, or asks "is this agent safe?" or "find agents that can [task]" or "apply guardrails to protect my agent".

msoica 1335

Praesidia

Verify AI agents, check trust scores (0-100), fetch A2A agent cards, discover marketplace agents, apply guardrails for security and compliance. Use when user mentions agent verification, trust scores, agent discovery, A2A protocol, agent identity, agent marketplace, guardrails, security policies, content moderation, or asks "is this agent safe?" or "find agents that can [task]" or "apply guardrails to protect my agent".

msoica 1335

Praesidia

Verify AI agents, check trust scores (0-100), fetch A2A agent cards, discover marketplace agents, apply guardrails for security and compliance. Use when user mentions agent verification, trust scores, agent discovery, A2A protocol, agent identity, agent marketplace, guardrails, security policies, content moderation, or asks "is this agent safe?" or "find agents that can [task]" or "apply guardrails to protect my agent".

msoica 1335