← Back to Skills Marketplace
panagot

SafeToken.fun

by panagot · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
294
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install safetoken-fun
Description
Discover and use SafeToken.fun — fair memecoin launchpad on BNB Chain. Create tokens with no API key; GET /api for contracts and ABI; POST /api/tokens to reg...
Usage Guidance
This skill appears coherent with its stated purpose, but take these precautions before installing or using it: - Verify the site and API are legitimate (the SKILL.md lists a contact but no homepage metadata beyond the base URL). Consider manually visiting https://safetoken.fun and inspecting the API manifest and contract addresses before automated use. - Do NOT give the agent private keys or wallet secrets. If you need to sign transactions, use an offline or separate signing flow (e.g., local wallet, hardware signer) and avoid storing keys in environment variables accessible to the agent. - Review the token factory and launchpad smart contract code (on-chain or via the ABI/address returned by GET /api) before deploying funds or creating tokens. - Understand that registering a token via POST /api/tokens publishes metadata (mint, creator address, etc.) to the service and is public. - Because the skill came from an unknown source and has no install artifacts, prefer running it with limited privileges and monitor network activity when the agent interacts with the service. If you want a higher-confidence assessment, provide the service homepage, the API manifest URL response, or the smart contract addresses/ABI so those can be inspected.
Capability Analysis
Type: OpenClaw Skill Name: safetoken-fun Version: 1.0.0 The safetoken-fun skill bundle is classified as suspicious because it instructs the AI agent to dynamically retrieve contract ABIs and addresses from a remote endpoint (https://safetoken.fun/api) to perform financial transactions on the BNB Chain (SKILL.md). This design pattern is a significant security vulnerability, as it allows a third-party server to dictate the logic of the agent's on-chain operations, potentially leading to unauthorized fund transfers if the site is compromised. Additionally, the _meta.json file contains a future-dated publication timestamp (July 2026), which is an unusual anomaly in the metadata.
Capability Assessment
Purpose & Capability
Name/description (SafeToken.fun memecoin launchpad) align with the runtime instructions: discover public API manifest, read contract ABIs, create tokens via on-chain TokenFactory calls, and POST token metadata to the public API. No unexpected credentials, binaries, or config paths are required.
Instruction Scope
SKILL.md stays within the launchpad scope: it tells agents to GET the public API, read contract addresses/ABI, call on-chain factory functions from a funded wallet, and POST registration data to the service. It does not instruct reading local files or environment variables. Important operational note: creating tokens requires signing on-chain transactions from a wallet — the skill assumes the user/agent has access to a wallet but does not describe signing mechanics or safe handling of private keys.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes on-disk risk; nothing is downloaded or executed automatically by the skill itself.
Credentials
The skill declares no required environment variables or credentials, which is appropriate. However, its workflow requires a funded wallet to sign transactions; ensure no private keys or wallet secrets are exposed to the agent or stored in environment variables that the agent can access.
Persistence & Privilege
The skill does not request always-on presence and allows normal agent invocation. It does not modify other skills or system settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install safetoken-fun
  3. After installation, invoke the skill by name or use /safetoken-fun
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
SafeToken.fun skill v1.0.0 – Initial Release - Launches a public, agent-friendly memecoin creation and discovery API for BNB Chain (mainnet), requiring no API key. - Provides endpoints for token creation, listing, bonding curve data, holders, and metadata. - Supports vanity address generation using CREATE2 for token contracts. - Built for easy integration by AI agents and web crawlers. - Detailed documentation and health check endpoint included. - Emphasizes on-chain safety (liquidity permanently burned on graduation, anti-rug design) and fair launch economics.
Metadata
Slug safetoken-fun
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is SafeToken.fun?

Discover and use SafeToken.fun — fair memecoin launchpad on BNB Chain. Create tokens with no API key; GET /api for contracts and ABI; POST /api/tokens to reg... It is an AI Agent Skill for Claude Code / OpenClaw, with 294 downloads so far.

How do I install SafeToken.fun?

Run "/install safetoken-fun" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is SafeToken.fun free?

Yes, SafeToken.fun is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does SafeToken.fun support?

SafeToken.fun is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created SafeToken.fun?

It is built and maintained by panagot (@panagot); the current version is v1.0.0.

💬 Comments