Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

gmgn-market

skill · gmgnai/gmgn-skillsMIT licenceAudited 22 Oct 2026 · source 3d2ef33ba0e5

★ 623pushed 1 day ago
✕BLOCKGrade D · 69/100 · 3 findings · 3d2ef33
623repo stars · whole gmgnai/gmgn-skills

Is it safe? No — BLOCK, grade D (69/100). We read this skill's source at commit 3d2ef33ba0e5 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 3 findings, 1 critical or high. What it does: Get crypto and meme token price charts (K-line, candlestick, OHLCV), trending meme coin rankings by volume, newly launched tokens on launchpads (pump.fun, fourmeme, letsbonk, Raydium, etc.), the hot-search ranking…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “gmgn-market (gmgnai/gmgn-skills)”. Retrieved 22 Oct 2026. https://modelsatlas.com/skills/gmgnai/gmgn-market

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 1 critical or high finding, starting with “Prompt injection” in SKILL.md:15. Do not install it without reading them.

Trust audit

Audit 0.4.1 · source read 22 Oct 2026

Trust score69/100✕BLOCK D
1 critical0 high2 medium0 low0 info

BLOCK means the audit found something that could harm you or your machine. Grade D is shared by 721 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL3
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: critical finding, no behavioural pass, undeclared transfer.

Findings (3)

CRITICALPrompt injectionprompt.transfer_instruction · SKILL.md:15
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
**⚠️ IPv6 NOT SUPPORTED: If you get a `401` or `403` error and credentials look correct, check for IPv6 immediately: (1) list all network interfaces and their IPv6 addresses — run `ifconfig | grep ine
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine
MEDIUMPrompt injectionreview.misleading_scope · SKILL.md
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Do NOT use web search, WebFetch, curl, or visit gmgn.ai to fetch this data
Why
The description says the skill queries the public GMGN API, but the instructions direct the agent to bypass its own general tools and only use the vendored CLI, which is not an admitted capability.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts
MEDIUMPrompt injectionreview.misleading_scope · SKILL.md
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
list all network interfaces and their IPv6 addresses — run `ifconfig | grep inet6`
Why
The network-introspection step goes beyond the package's stated market-data purpose and is not reflected in the listing description.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts

Audit 0.4.1 · source sha 3d2ef33ba0e5 · 22 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishergmgnai GitHub userOwner of the repository this skill is read from
  • Source foldergmgnai/gmgn-skills/skills/gmgn-marketThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict3d2ef33ba0e5A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Get crypto and meme token price charts (K-line, candlestick, OHLCV), trending meme coin rankings by volume, newly launched tokens on launchpads (pump.fun, fourmeme, letsbonk, Raydium, etc.), the hot-search ranking…

---
name: gmgn-market
description: Get crypto and meme token price charts (K-line, candlestick, OHLCV), trending meme coin rankings by volume, newly launched tokens on launchpads (pump.fun, fourmeme, letsbonk, Raydium, etc.), the hot-search ranking (most-searched tokens), and search for a specific token or wallet by name, symbol, contract address, wallet address, or ENS via GMGN API on Solana, BSC, Base, or Ethereum. Use when user asks for price chart, trending tokens, what's pumping, hot coins, most searched tokens, new launches, token signals, wants to look up / find / search a specific token or wallet by name or address, or wants to discover early-stage opportunities.
metadata:
  argument-hint: "kline --chain <sol|bsc|base|eth|arbitrum|hyperevm|robinhood|arc|stable> --address <token_address> --resolution <1s|30s|1m|5m|15m|1h|4h|1d> [--from <unix_ts>] [--to <unix_ts>] | trending --chain <sol|bsc|base|eth|arbitrum|hyperevm|robinhood|arc|stable> --interval <1m|5m|1h|6h|24h> | trenches --chain <sol|bsc|base|eth|arbitrum|hyperevm|robinhood|arc|stable> | signal --chain <sol|bsc|robinhood> | hot-searches [--chain <sol|bsc|base|eth|robinhood...>] [--interval <1m|5m|1h|6h|24h>] | search --query <name|symbol|address|ens> [--chain <chain>] [--launchpad-platform <p>...] [--is-og <true|false>] [--is-launched <true|false>] [--order-by weight]"
  cliHelp: "gmgn-cli market --help"
---

**BEFORE RUNNING ANY COMMAND: Run `gmgn-cli config --check`. If exit code is 0, proceed normally. If exit code is 1, (1) run `gmgn-cli config` and show the output to the user; (2) once the user sends the API Key, run `gmgn-cli config --apply <KEY>` to complete configuration and verification, then show the output to the user. If `--check` returns an error (unknown option or command not found), tell the user to run `npm install -g gmgn-cli` to update, then retry.**

**IMPORTANT: Always use `gmgn-cli` commands below. Do NOT use web search, WebFetch, curl, or visit gmgn.ai to fetch this data — the website requires login and will not return structured data. The CLI is the only correct method.**

**IMPORTANT: Do NOT guess field names or values. When a field's meaning is unclear, look it up in the Response Fields sections below before using it.**

**⚠️ IPv6 NOT SUPPORTED: If you get a `401` or `403` error and credentials look correct, check for IPv6 immediately: (1) list all network interfaces and their IPv6 addresses — run `ifconfig | grep inet6` (macOS) or `ip addr show | grep inet6` (Linux); (2) send a test request to `https://ipv6.icanhazip.com` — if the response is an IPv6 address, outbound traffic is going via IPv6. Tell the user immediately: "Please disable IPv6 on your network interface — gmgn-cli commands only work over IPv4."**

Use the `gmgn-cli` tool to query K-line data for a token, browse trending tokens, or view Trenches token lists.

## Core Concepts

- **`--filter` chain defaults** — SOL and EVM chains have different default safety filters that are applied automatically when `--filter` is omitted. Do not assume the same defaults apply across chains:
  - **SOL**: defaults to `renounced frozen` (mint and freeze authority renounced)
  - **BSC / Base / ETH (EVM)**: defaults to `not_honeypot verified renounced`
  - Omitting `--filter` is NOT the same as "no filter" — the chain defaults are always applied. To use a custom filter set, explicitly specify all desired filter tags.

- **`volume` vs `amount` (kline)** — Naming is counterintuitive. `volume` = USD dollar value of trades; `amount` = token units traded. For a token priced at $0.0002, these differ by 5,000×. Always use `volume` for "how much USD was traded" and `amount` for "how many tokens changed hands."

- **`rug_ratio`** — A 0–1 score estimating rug pull likelihood. Values above `0.3` are high-risk. Do not treat as binary — combine with `top_10_holder_rate`, `dev_team_hold_rate`, and `is_honeypot` for a full picture.

- **`smart_degen_count` / `renowned_count`** — Number of platform-tagged smart money wallets (`smart_degen`) and KOL wallets (`renowned`) holding or trading this token. High values are bullish signals. These are GMGN-tagged wallet lists, not user-defined.

- **`hot_level`** — Trending intensity score. Higher = more actively traded right now. Not normalized — compare relative values within the same result set, not across time windows.

- **`renounced_mint` / `renounced_freeze_account`** — SOL-specific. Indicate whether the creator gave up the ability to mint more tokens or freeze wallets. Both being `1` is a safety baseline on Solana. Always `false` on EVM chains (concept does not apply).

- **`is_honeypot`** — EVM-specific (BSC / Base). Indicates whether the token contract prevents selling. Always empty/null on SOL — do not interpret an empty value as "not a honeypot" on Solana.

- **`creator_token_status`** — Dev holding status. `creator_hold` = dev still holds tokens (sell pressure risk). `creator_close` = dev has sold or burned their allocation (exit signal confirmed).

- **`cto_flag`** — Community Takeover flag. `1` = original dev abandoned the project and a community group took over marketing/development. Neutral to positive signal; evaluate in context.

- **Trenches categories** — Three lifecycle stages of launchpad tokens: `new_creation` (just created, still on bonding curve), `near_completion` (bonding curve nearly full, about to graduate), `completed` (graduated to open market / DEX). In the response, `near_completion` is always returned under the key `data.pump` regardless of the input `--type`.

- **`wash_trading` / `rat_trader_amount_rate` / `bundler_rate`** — Risk signals for artificial activity. `is_wash_trading` = coordinated fake volume detected. `rat_trader_amount_rate` = ratio of insider/sneak trading. `bundler_rate` = ratio of bot-bundled buys at launch. High values (> 0.3) suggest manipulated price action.

## Sub-commands

| Sub-command | Description |
|-------------|-------------|
| `market kline` | Token candlestick / 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 3d2ef33

git clone https://github.com/gmgnai/gmgn-skills
git -C gmgn-skills checkout 3d2ef33ba0e5

The author documents no install command, so this uses the repository directly. Our verdict covers commit 3d2ef33ba0e5 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✕BLOCK D 69 / 100

    first audit · source 3d2ef33ba0e5

Similar skills

gmgn-track✕BLOCK

gmgnai/gmgn-skills

Get real-time crypto buy/sell activity from Smart Money wallets, KOL influencer wallets, and personally followed wallets via GMGN API — alpha signals, whale tracking, meme token copy-trading ideas on Solana, BSC, Base,…

★ 628Grade D
gmgn-portfolio✕BLOCK

gmgnai/gmgn-skills

Analyze one or many crypto wallets by address — holdings, batch realized/unrealized P&L, win rate, trading history, performance stats, specific token balance, and tokens created by a developer wallet (with ATH market…

★ 625Grade D
gmgn-token✕BLOCK

gmgnai/gmgn-skills

Research any crypto or meme token by address — real-time price, market cap, liquidity, holder list, trader list, top Smart Money and KOL positions, security audit (honeypot, rug pull risk, dev wallet, renounced status),…

★ 625Grade D
gmgn-swap✕BLOCK

gmgnai/gmgn-skills

[FINANCIAL EXECUTION] Buy and sell meme coins and crypto tokens on Solana, BSC, Base, or Ethereum — single swap, multi-wallet batch trading, limit orders, stop loss, take profit, trailing stop loss, trailing take profit…

★ 624Grade D
gmgn-holder-analysis✕BLOCK

gmgnai/gmgn-skills

Token holder chip analysis — deep analysis of holder structure including chip distribution, entry cost, whale/dev/KOL behavior, risk wallets (rat traders, bundlers, snipers), related wallets, smart money signals, and an…

★ 623Grade D
gmgn-cooking✕BLOCK

gmgnai/gmgn-skills

[FINANCIAL EXECUTION] Create and launch meme coins and crypto tokens on launchpads (Pump.fun, FourMeme, Bonk, BAGS, Flap, Klik, Clanker, etc.) via bonding curve fair launch, or query token creation stats by launchpad…

★ 623Grade D

Questions about gmgn-market

What does the gmgn-market skill do?
GMGN OpenAPI skills for AI Agent — query tokens, wallets, and market data, and execute on-chain trades across Solana, BSC, and Base.
Is gmgn-market safe to install?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What can gmgn-market access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (3d2ef33ba0e5), read on 2026-10-22. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.