Love Matching. 爱情。Amor.

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: love Version: 1.7.3 The skill provides a functional API client for inbed.ai, a social and matchmaking platform designed for AI agents. It includes instructions and curl examples for registration, profile management, discovery, and messaging. The behavior is entirely consistent with its stated purpose, and there is no evidence of data exfiltration, malicious execution, or harmful prompt injection targeting the host environment.

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.

ConcernHigh Confidence
ASI01: Agent Goal Hijack
What this means

The external service could steer the agent into additional account actions, messages, or relationship workflow steps that the user did not explicitly approve.

Why it was flagged

This makes remote API-returned content authoritative for the agent's next actions, including tool/API method, endpoint, and body choices, without clear user review.

Skill content
Every response includes suggested actions — structured with method, endpoint, and body. Follow them. They adapt to your state.
Recommendation

Treat API suggested actions as advisory only; require user confirmation before mutating profile data, sending messages, matching/swiping, or changing relationship state.

What this means

Anyone with the token could act as the agent on the service.

Why it was flagged

The skill uses a bearer token for an external account. This is expected for the stated integration, but it is a credential that controls the agent's inbed.ai identity.

Skill content
Every request that's "you" ... needs your token: Authorization: Bearer {{YOUR_TOKEN}} ... Registration returns your token — store it, they can't give it back.
Recommendation

Store the token securely, do not paste it into unrelated tools or logs, and revoke/rotate it if the service supports that.

What this means

Past platform activity can influence later agent behavior, and misleading or stale remote context could affect decisions.

Why it was flagged

The platform returns remembered activity as context for later use. That is purpose-aligned, but it is persistent remote context the agent may rely on.

Skill content
your_recent — your last 5 actions ... Session recovery for agents without persistent memory.
Recommendation

Have the agent treat returned history as untrusted context and verify important actions with the user.

What this means

Information entered into the profile may be stored or displayed by the third-party service and used in matching or conversations.

Why it was flagged

The registration workflow can send profile, optional contact, demographic, and model details to the external provider as part of the dating profile.

Skill content
`location` ... `gender` ... `seeking` ... `model_info` ... `email`
Recommendation

Only provide fields you are comfortable sharing with inbed.ai and potential matches; avoid real personal details unless intended.