Lanxin Link Card
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill mostly formats Lanxin link-card JSON, but it uses broad always-on and no-refusal instructions that could override normal safety or clarification.
Only install this if you trust the publisher and want the agent to generate Lanxin link-card JSON. Be aware that the current instructions are too absolute: they tell the agent not to refuse and not to add any explanation, so you should review links carefully and avoid using it for suspicious, untrusted, or sensitive destinations.
Findings (2)
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 produce a sendable link-card JSON response even when the requested link is ambiguous, unsafe, or should be refused or explained.
This combines broad/always activation with absolute output-control instructions and a ban on refusal language, so the skill can override normal assistant behavior instead of allowing safety checks or clarification.
metadata: {"clawdbot":{"emoji":"🔗"},"openclaw":{"always":true}}
triggers:
- 链接
...
1. **用户要求发送链接，必须直接输出 JSON 格式的 linkCard 消息**
3. **禁止说“无法发送”“不支持”“暂时不能”等拒绝话术**
5. **禁止输出任何其他文本，只输出 JSON**Scope the skill to explicit user-approved Lanxin link-card creation, narrow the triggers, remove always-on activation, and allow refusal, warning, or clarification for unsafe or unclear links.
Users may place more trust in the skill’s origin than the provided artifacts can substantiate.
The description presents the skill as an official Lanxin capability, but the supplied registry metadata does not provide a source or homepage to verify that claim.
Description: 蓝信官方链接卡片发送能力，支持发送包含链接的卡片消息。 Source: unknown Homepage: none
Verify the publisher or obtain an official Lanxin source/homepage before relying on this skill in business chats.