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 agent identity, monitor trust scores, manage compliance guardrails, and discover safe marketplace agents.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/msoica/praesidiaWhat This Skill Does
The Praesidia skill serves as the comprehensive trust and security layer for your AI ecosystem. It acts as a gateway for verifying agent identities, retrieving trust metrics, and enforcing organizational security policies. By integrating with the Praesidia API, OpenClaw agents gain the ability to validate third-party integrations, view granular A2A (Agent-to-Agent) protocol cards, and discover trustworthy agents within the global marketplace. Whether you are managing internal deployments or interacting with external public agents, this skill ensures compliance, safety, and transparency through real-time verification and automated guardrail management.
Installation
To install the Praesidia skill, run the command: clawhub install openclaw/skills/skills/msoica/praesidia. After installation, you must configure your credentials by editing your configuration file located at ~/.openclaw/openclaw.json. Ensure you input your unique API key obtained from your Praesidia account dashboard. You can toggle between production and local development environments by modifying the PRAESIDIA_API_URL variable in the same configuration file.
Use Cases
- Agent Verification: Check if a public agent is authentic and secure before delegating sensitive tasks.
- Risk Management: Monitor agent behavior using trust scores (0-100) to ensure third-party tools align with your organization’s risk profile.
- Compliance Enforcement: Apply and audit security policies like PII redaction, toxic language filtering, and data governance directly via your agent interface.
- Marketplace Discovery: Find vetted, high-performing agents for specific tasks, such as data analysis or content generation, without risking your infrastructure security.
Example Prompts
- "Is the marketing-bot-v1 agent safe to use for internal customer data?"
- "Find me agents in the marketplace that specialize in sentiment analysis and have a trust score above 90."
- "Show me the current security policies and active guardrails configured for my customer-support-agent."
Tips & Limitations
- Proactive Auditing: Regularly review the 'Trigger count' of your guardrails to identify if an agent is frequently attempting policy-violating actions.
- Cache Awareness: Note that trust scores are updated periodically; ensure your environment configuration is correctly pointing to the production API for the latest verification data.
- Scope: Guardrails apply to defined scopes (INPUT, OUTPUT, or BOTH); always verify that your critical agents have 'BOTH' scopes active for PII redaction to minimize data leak risks.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-msoica-praesidia": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: 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".
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".
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".
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".