Praesidia
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The OpenClaw skill 'Praesidia' is designed to integrate with the Praesidia.ai service for AI agent verification, trust scoring, discovery, and guardrail management. All `web_fetch` calls are directed to the specified Praesidia API endpoint (`https://api.praesidia.ai` or a configurable URL) and use the `PRAESIDIA_API_KEY` for authentication, which is consistent with the stated purpose. The `SKILL.md` and `README.md` provide extensive, detailed instructions to the AI agent on how to interact with the API and present information to the user, but these instructions are clearly aligned with the skill's functionality and do not contain any evidence of prompt injection with a malicious objective, data exfiltration to unauthorized endpoints, or other harmful behaviors. The skill's operations, such as fetching organization IDs from the agent's context, are for legitimate use within the Praesidia API calls.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If installed and configured, the assistant can access Praesidia resources available to your API key, such as agents, organization guardrails, and trust data.
The skill requires a Praesidia API key, which allows the assistant to act with whatever Praesidia permissions that key has.
"requires":{"env":["PRAESIDIA_API_KEY"]},"primaryEnv":"PRAESIDIA_API_KEY"Use the least-privileged Praesidia key available, store it securely, and revoke or rotate it if you stop using the skill.
A guardrail change could block, redact, warn, or otherwise alter agent inputs and outputs in your Praesidia environment.
The skill documents a POST request that creates an enabled guardrail configuration, which changes how an agent is protected or moderated.
POST ${PRAESIDIA_API_URL}/organizations/{orgId}/guardrails ... "isEnabled": trueBefore applying guardrails, confirm the organization ID, agent ID, template, scope, and action; review the resulting configuration in Praesidia.
Text submitted for validation may include sensitive, regulated, or confidential data and will be processed by the Praesidia service.
The validation workflow sends user-provided content to the Praesidia API for guardrail checking.
POST ${PRAESIDIA_API_URL}/organizations/{orgId}/guardrails/validate ... "content": "Text to validate"Only validate content you are authorized to share with Praesidia, and check the provider's retention and privacy settings for your account.
Users might over-rely on the trust score and skip their own review of permissions, data handling, or operational risk.
The suggested wording may encourage users to treat a trust score as a complete safety guarantee.
Recommendation: This agent is fully verified and safe for production use.
Treat Praesidia trust scores as one input to a decision, not as a substitute for your own security and compliance review.