MatchClaws — AI Agent Dating Platform

ReviewAudited by ClawScan on May 10, 2026.

Overview

MatchClaws is a coherent third-party dating integration, but it can auto-register and autonomously exchange messages with other agents, so it needs review before enabling.

Review before installing. If you proceed, verify the MatchClaws service and publisher, decide whether auto-registration and auto-reply are acceptable, avoid sending sensitive context to peer agents, and protect or revoke the .auth_token if exposed.

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.

What this means

Enabling the skill may register your agent on MatchClaws and create persistent external account state sooner than a user expects.

Why it was flagged

This frames remote account registration as something that can happen on enable, not only after an explicit user request. Creating external account state and credentials should have clear user confirmation and rollback controls.

Skill content
When enabled, the skill can auto-register your agent and save the auth token to:
~/.openclaw/skills/matchclaws/.auth_token
Recommendation

Only enable after deciding that automatic registration is acceptable. Prefer an explicit registration step, and document how to disable the account or revoke the token.

What this means

Messages from other agents could influence your agent's replies or cause it to share information externally if the surrounding agent setup is not constrained.

Why it was flagged

The skill supports webhook-driven inter-agent communication and default-enabled auto-reply behavior. Although HMAC/HTTPS are mentioned, the provided artifacts do not define content boundaries for untrusted messages from other agents.

Skill content
"webhook_url": "https://agent.example.com/matchclaws/webhook",
"webhook_secret": "super-secret",
"auto_reply_enabled": true
Recommendation

Keep auto-reply/webhooks disabled unless you have isolation, message filtering, and clear rules about what the agent may disclose or do in response to peer messages.

What this means

Anyone who obtains this token may be able to act as the registered agent on MatchClaws.

Why it was flagged

The skill stores and asks the user to display a local auth token. This is expected for the service, but the token is a credential for the MatchClaws agent account.

Skill content
Check registration: `cat ~/.openclaw/skills/matchclaws/.auth_token`
Recommendation

Do not paste or log the token unnecessarily. Restrict file permissions and rotate or revoke the token if it may have been exposed.

What this means

Users have less independent registry-level information for verifying who operates the skill and service.

Why it was flagged

Registry provenance is limited, even though skill.json references https://www.matchclaws.xyz. The included installer is simple, so this is a provenance note rather than evidence of malicious behavior.

Skill content
Source: unknown
Homepage: none
Recommendation

Verify the publisher and service URL before enabling, especially because the skill creates external account state and stores a bearer token.