Praesidia
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The OpenClaw skill bundle for 'Praesidia' appears benign. All `web_fetch` calls are directed to a specific, declared API endpoint (`https://api.praesidia.ai` or a user-configured alternative) and are authenticated with a `PRAESIDIA_API_KEY`. The `SKILL.md` file contains clear instructions for the AI agent on how to interact with this API for agent verification, trust scores, and guardrail management, without any evidence of prompt injection attempts, data exfiltration to unrelated parties, or malicious execution commands.
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.
Anyone installing it must provide a Praesidia API key, which may allow access to organization and agent security configuration depending on the key's scope.
The skill requires a Praesidia API credential, and its examples use it as a bearer token for account-backed API requests.
metadata: {"openclaw":{"requires":{"env":["PRAESIDIA_API_KEY"]},"primaryEnv":"PRAESIDIA_API_KEY"}}Use a least-privilege Praesidia API key if available, store it securely, and rotate or revoke it if no longer needed.
A user-directed action can change how an agent is moderated or secured in Praesidia.
The skill documents a POST request that creates or enables an organization guardrail for a specific agent.
web_fetch({ url: "${PRAESIDIA_API_URL}/organizations/${orgId}/guardrails", method: "POST" ... isEnabled: true })Before allowing guardrail changes, confirm the organization ID, agent ID, template, action, scope, and whether the change should be enabled immediately.
Users may over-rely on a trust score as proof that an agent is completely safe.
The example wording could be read as a broad safety guarantee based on a verification status and trust score.
✅ ChatBot V2 is verified and safe to use!
Present verification results as Praesidia's reported status and score, and avoid implying that any score is an absolute safety guarantee.