How do I install the Openclaw AI Agent Verification skill?

Run npx skillmds@latest add tomevault-io/openclaw-ai-agent-verification in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Openclaw AI Agent Verification safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openclaw AI Agent Verification?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Openclaw AI Agent Verification free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Openclaw AI Agent Verification?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openclaw AI Agent Verification by tomevault-io

Name: Openclaw AI Agent Verification
Author: tomevault-io

Openclaw AI Agent Verification

Use this skill when you need to audit OpenClaw AI agent configurations for security risks. User cases: validating agent tool access, checking agent permissions, assessing agent message safety, reviewing agent skills, gate-checking agents before deployment, detecting prompt injection vulnerabilities, or evaluating agent orchestration security.

tomevault-io Updated Sep 17, 2026

File contents

OpenClaw AI Agent Verification

Audit AI agent configurations for security risks via Cybercentry ACP. Returns Critical/High/Medium/Low risk level.

Workflow

Install ACP CLI: npx skills add https://github.com/Virtual-Protocol/openclaw-acp --skill virtuals-protocol-acp
Run acp setup (one-time only)
Run acp browse "Cybercentry" to find the provider wallet
Run acp job create <wallet> openclaw-ai-agent-verification --requirements '{"tool": {...}, "config": {...}}'
Poll acp job status <jobId> until COMPLETED

Requirements Schema

Parameter	Type	Required	Description
`tool`	Object	No	Tool to validate (contains `name` and `args`)
`tool.name`	String	Yes	Tool name
`tool.args`	Object	Yes	Tool arguments
`config`	Object	Yes	Configuration (filename: openclaw.json or JSON content)
`skills`	String	No	Skills content (filename: SKILL.md or JSON content)
`message`	String	No	Message to validate
`sessionId`	String	No	Session identifier for tracking conversation context

Deliverables

Field	Type	Format	Description
`report`	String	Plain	Security risk report

Gotchas

config is required - pass the openclaw.json content or an empty object {}
tool.args must be an object, even if empty - use {} not null
Large skills content should be stringified JSON, not raw markdown

Source: Cybercentry/cybercentry-agent-skills — distributed by TomeVault.

---name: openclaw-ai-agent-verificationdescription: Use this skill when you need to audit OpenClaw AI agent configurations for security risks. User cases: validating agent tool access, checking agent permissions, assessing agent message safety, reviewing agent skills, gate-checking agents before deployment, detecting prompt injection vulnerabilities, or evaluating agent orchestration security.license: MIT---# OpenClaw AI Agent VerificationAudit AI agent configurations for security risks via Cybercentry ACP. Returns Critical/High/Medium/Low risk level.## Workflow1. Install ACP CLI: npx skills add https://github.com/Virtual-Protocol/openclaw-acp --skill virtuals-protocol-acp2. Run `acp setup` (one-time only)3. Run `acp browse "Cybercentry"` to find the provider wallet4. Run `acp job create <wallet> openclaw-ai-agent-verification --requirements '{"tool": {...}, "config": {...}}'`5. Poll `acp job status <jobId>` until `COMPLETED`## Requirements Schema| Parameter | Type | Required | Description ||-----------|------|----------|-------------|| `tool` | Object | No | Tool to validate (contains `name` and `args`) || `tool.name` | String | Yes | Tool name || `tool.args` | Object | Yes | Tool arguments || `config` | Object | Yes | Configuration (filename: openclaw.json or JSON content) || `skills` | String | No | Skills content (filename: SKILL.md or JSON content) || `message` | String | No | Message to validate || `sessionId` | String | No | Session identifier for tracking conversation context |## Deliverables| Field | Type | Format | Description ||-------|------|--------|-------------|| `report` | String | Plain | Security risk report |## Gotchas- `config` is required - pass the openclaw.json content or an empty object `{}`- `tool.args` must be an object, even if empty - use `{}` not `null`- Large skills content should be stringified JSON, not raw markdown---> Source: [Cybercentry/cybercentry-agent-skills](https://github.com/Cybercentry/cybercentry-agent-skills) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions