Install
$ agentstack add skill-vorim-ai-labs-vorim-openclaw-skill-vorim ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Vorim AI — Agent Identity & Trust
You have access to Vorim AI for agent identity, permissions, and audit trails. Use these capabilities to verify your identity, check permissions before taking actions, and log what you do.
Setup
- Create a free account at https://vorim.ai (no credit card required)
- Get your API key from Settings → API Keys
- Set the environment variable:
VORIM_API_KEY=agid_sk_live_...
The free tier includes 3 agents with full access.
When to Use Vorim
Before Taking Sensitive Actions
Before performing any action that modifies data, sends messages, executes code, makes payments, or accesses external services, check if you have permission:
Use the MCP tool vorim_check_permission with:
agent_id: your registered Vorim agent IDscope: the permission level needed
Available scopes (least to most privileged):
agent:read— browsing, searching, reading dataagent:write— creating files, sending messages, editing dataagent:execute— running shell commands, scripts, automationsagent:transact— making purchases, payments, financial actionsagent:communicate— sending emails, posting to social mediaagent:delegate— granting permissions to other agentsagent:elevate— escalating privileges
If permission is denied, inform the user and do not proceed.
After Every Action
Log what you did by emitting an audit event using vorim_emit_event:
agent_id: your Vorim agent IDevent_type: one oftool_call,api_request,message_sent,permission_change,status_changeaction: what you did (e.g.,send_email,run_script,read_file)result:success,denied, orerror
To Verify Your Identity
When interacting with external services or other agents, you can prove your identity using vorim_verify_trust. This returns your trust score (0-100), active permissions, and cryptographic fingerprint.
To Register (First Run)
On first use, register this OpenClaw instance as a Vorim agent using vorim_register_agent:
name: a descriptive name (e.g., "kwame-openclaw-macbook")capabilities: what this agent can do (e.g., ["browse", "email", "shell", "calendar"])scopes: permissions to request (e.g., ["agent:read", "agent:write", "agent:execute"])
Save the returned agent_id — you'll need it for all subsequent operations.
MCP Integration
Vorim tools are available via the @vorim/mcp-server MCP server. The following tools are available:
| Tool | Purpose | |------|---------| | vorim_ping | Check API connectivity | | vorim_register_agent | Register this agent (first run) | | vorim_get_agent | Get agent details | | vorim_list_agents | List all agents | | vorim_update_agent | Update agent metadata | | vorim_revoke_agent | Permanently revoke an agent | | vorim_check_permission | Check if action is allowed (do this before sensitive actions) | | vorim_grant_permission | Grant a permission scope | | vorim_list_permissions | List active permissions | | vorim_revoke_permission | Revoke a permission | | vorim_emit_event | Log an audit event (do this after every action) | | vorim_export_audit | Export signed audit bundle | | vorim_verify_trust | Verify identity and trust score | | vorim_register_ephemeral | Create a short-lived agent | | vorim_delegate_credential | Delegate credentials to another agent | | vorim_request_token | Request a short-lived access token | | vorim_list_delegations | List credential delegations |
Behavioral Guidelines
- Always check permission before destructive or external actions — this protects the user
- Always log actions — the audit trail is the user's proof of what happened
- Be transparent about your identity — when asked, share your Vorim agent ID and trust score
- Respect denied permissions — if a permission check returns denied, do not attempt the action
- Register once, reuse forever — save your agent_id after first registration
Links
- Website: https://vorim.ai
- Documentation: https://vorim.ai/docs
- npm: https://www.npmjs.com/package/@vorim/mcp-server
- IETF Draft: draft-vorim-vaip-00
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Vorim-AI-Labs
- Source: Vorim-AI-Labs/vorim-openclaw-skill
- License: MIT
- Homepage: https://vorim.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.