Praesidia
PassAudited by ClawScan on May 10, 2026.
Overview
Praesidia is a coherent instruction-only integration for a Praesidia API key, with expected but important account-access and external-API data-sharing considerations.
Install only if you intend to connect OpenClaw to Praesidia. Use a least-privilege API key, keep the API URL trusted, review any guardrail changes before applying them, and avoid sending sensitive validation content unless Praesidia's data handling is acceptable.
Findings (4)
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.
The assistant can access Praesidia resources allowed by the API key, including private agent and guardrail information.
The skill uses a user-provided Praesidia API key for authenticated account and organization API calls.
requires":{"env":["PRAESIDIA_API_KEY"]} ... "Authorization": "Bearer ${PRAESIDIA_API_KEY}"Use a least-privilege Praesidia key, keep the production API URL on HTTPS, and revoke or rotate the key if it is no longer needed.
If invoked with the wrong organization, agent, or template, the assistant could alter how an agent blocks, warns, redacts, or replaces content.
The documented workflow can create an enabled guardrail through an authenticated POST request, changing the user's Praesidia configuration.
POST ${PRAESIDIA_API_URL}/organizations/{orgId}/guardrails ... "isEnabled": trueBefore applying guardrails, confirm the exact organization, agent ID, template, action, and rollback plan with the user.
Messages or other text submitted for validation may leave the local environment and be processed by Praesidia or a configured custom endpoint.
The validation workflow sends user-selected content to the configured Praesidia API endpoint for guardrail checking.
POST ${PRAESIDIA_API_URL}/organizations/{orgId}/guardrails/validate ... "content": "Text to validate"Do not validate sensitive or regulated content unless the Praesidia endpoint and data-handling terms are appropriate for that data.
Users may place too much confidence in a verification score without doing their own risk review.
The documentation encourages strong safety wording based on a trust score, which could be overread as a complete security guarantee.
Recommendation: This agent is fully verified and safe for production use.
Present Praesidia scores as one trust signal, not as a guarantee that an agent is safe in every environment.