crypto skill

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill is a coherent read-only crypto data API, but it asks users to send a long-lived bearer token to an unknown raw-IP HTTP server.

Only use this skill if you trust the operator and are comfortable sending queries and a service-specific token to the listed server. Prefer waiting for HTTPS, a domain-backed service, explicit credential metadata, and revocable tokens; verify any crypto/KOL information independently before acting on it.

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

Someone on the network path could capture the API token and consume or abuse the user's quota/account for this service.

Why it was flagged

The skill requires a long-lived bearer token and directs it to a plaintext HTTP raw-IP service. Authentication is disclosed and purpose-aligned, but the token is not protected in transit and could be reused if intercepted.

Skill content
**认证方式**: Bearer Token ... Token有效期:1年 ... **Base URL**: `http://88.222.241.169`
Recommendation

Do not reuse any other secret as this token. Prefer an HTTPS domain, short-lived/revocable tokens, and an explicit credential declaration before configuring it.

What this means

Users have limited assurance that they are connecting to the intended service, and responses could be tampered with on the network path.

Why it was flagged

The only declared API server is a raw IP address over HTTP. This is not local code installation, but it gives users little provenance or transport assurance for the service they are trusting.

Skill content
"servers": [{ "url": "http://88.222.241.169", "description": "生产服务器" }]
Recommendation

Ask the maintainer for a stable HTTPS domain, public service provenance, and clear documentation of who operates the API.

What this means

Contract addresses or token interests entered by the user may be visible to the listed third-party services.

Why it was flagged

The documented workflow intentionally sends contract-address lookups to multiple external providers, including a Jina AI proxy for GMGN. This is disclosed and central to the purpose, but it expands where user queries are sent.

Skill content
DexScreener直接访问 ... GMGN via Jina AI ... Binance Web3
Recommendation

Avoid querying sensitive or unpublished token information through the external providers unless you are comfortable sharing those lookups.

What this means

The agent may surface unverified trading narratives or community content that should not be treated as authoritative advice.

Why it was flagged

The skill retrieves community chat summaries and KOL content. That content is purpose-aligned, but it is third-party social/market text that could be opinionated, inaccurate, or unsafe to treat as instructions.

Skill content
飞书群聊AI总结 - 查询各大KOL群组的每日聊天总结 ... 二级KOL数据 - 获取专业KOL的代币分析和推荐
Recommendation

Treat returned chat/KOL content as untrusted data, verify with independent sources, and do not allow returned text to override the user's instructions.