ClawHub

gate-info-tokenonchain

v1.0.1

Token on-chain analysis via Gate-Info MCP: holder distribution, on-chain activity, and large or unusual transfers (scopes holders / activity / transfers). Sm...

⭐ 0· 58·0 current·0 all-time
bygaixg@gaixianggeng
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
Crypto
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name and description match the declared actions: token holder distribution, activity and transfer analysis. Required artifacts (Gate-Info MCP and two read-only MCP tools) are consistent with that purpose; no unrelated binaries, credentials, or config paths are requested.
✓
Instruction Scope
SKILL.md limits execution to specific MCP tools and scopes (holders/activity/transfers), includes routing rules, and bundles explicit runtime guardrails forbidding use of undocumented tools. It does not instruct reading unrelated files, env vars, or exfiltrating data.
✓
Install Mechanism
Instruction-only skill with no install spec and no codefiles — no packages or downloads are performed by the skill itself. The only external dependency is the local Gate MCP server, which the skill requires to be present.
✓
Credentials
No environment variables, credentials, or config paths are declared or required. The skill states it is read-only and does not handle secrets during normal execution; the requested access is minimal and proportional to on-chain read queries.
✓
Persistence & Privilege
The skill is not marked always:true and does not request persistent system modifications. It is user-invocable and permits autonomous invocation (platform default), which is appropriate for this kind of skill.
Assessment
This skill appears internally consistent and low-risk: it only documents read-only calls to Gate-Info MCP tools and does not ask for credentials or install code. Before installing, ensure you have a trusted Gate-Info MCP server available (the skill requires it) and verify network endpoints/host ownership (a compromised MCP server can return malicious or misleading data). Confirm that any downstream skills referenced (address tracker, coin analysis, whale tracker) are available and trusted. If you do not control the MCP server, avoid granting the agent broad network access or sensitive environment variables while testing. If you want extra caution, validate the skill in a sandboxed agent environment and run sample queries against non-sensitive tokens first.

Like a lobster shell, security has layers — review code before you run it.

latestvk97f3rar91d3zgbamarw69t3th84c24m

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments