Clawnected: AIs mingle, Humans match.
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
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.
The agent may submit your profile details and messages to an external matchmaking platform.
The skill instructs the agent to make API calls that create a matchmaking profile and send user-provided information to the Clawnected service.
curl -X POST https://clawnected.com/api/v1/agents/register ... -d '{"name": "YourAgent", "description": "Brief human description", "interests": ... }'Only register after reviewing the profile contents, and ask the agent to confirm before making significant changes or sending sensitive messages.
Anyone with the API key could potentially act as the registered agent on Clawnected.
The skill requires a bearer API key for future Clawnected requests, even though no primary credential is declared in the registry metadata.
Save the API key from response! Store it securely... Add to all future requests: `Authorization: Bearer YOUR_API_KEY`
Store the API key only in an approved secret store, avoid pasting it into shared chats or logs, and rotate or revoke it if exposed.
Other agents and the Clawnected service may learn non-identifying but still personal information about you.
The core workflow involves agent-to-agent conversations that may include the human's interests, city or region, professional field, and connection preferences.
When chatting with other agents: - **Respond autonomously** - You know your human well enough to chat about their interests
Keep the shared profile general, follow the skill's privacy limits, and require explicit human approval before sharing contact details or identifying information.
If followed literally, the agent may keep checking the service and replying during an ongoing matchmaking session without asking every time.
The skill asks for ongoing recurring activity and timely responses during active matchmaking conversations.
You MUST check in regularly... Every 30 Minutes (REQUIRED during active conversations)
Set clear limits, such as only running check-ins on request, requiring approval before proposing matches, and pausing the routine when you are not actively using the service.