Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

TrencherAI — Base Chain Intelligence

v1.0.1

Real-time AI scoring for Base chain tokens via x402 micropayments. Score any token 0-100 with smart money signals, pattern win rate, launchpad context, and B...

0· 102·0 current·0 all-time
byBasedJaider@soynull

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for soynull/trencherai-base-intelligence.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "TrencherAI — Base Chain Intelligence" (soynull/trencherai-base-intelligence) from ClawHub.
Skill page: https://clawhub.ai/soynull/trencherai-base-intelligence
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install trencherai-base-intelligence

ClawHub CLI

Package manager switcher

npx clawhub@latest install trencherai-base-intelligence
Security Scan
Capability signals
CryptoRequires walletCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description (token scoring on Base) matches the runtime instructions: all endpoints are token-scoring, hot-feeds, and smart-money activity. The declared lack of required binaries/env/config is consistent with an instruction-only wrapper that delegates payments to the client-side x402 flow.
Instruction Scope
Instructions are narrowly scoped to calling api.aitrencher.xyz endpoints and handling an x402 payment flow; they do not ask the agent to read unrelated files or system-wide secrets. However, the doc includes a code example that uses Coinbase CDP credentials (apiKeyId, apiKeySecret) for signing payments — the SKILL.md does not declare these as required env vars, so callers must supply them to their agent/client. The agent will need to perform wallet signing or provide Coinbase CDP keys to make payments, which increases the risk of accidental charges or credential exposure if not managed carefully.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is written to disk by the skill itself. This is the lowest install risk.
!
Credentials
The skill declares no required environment variables, yet its payment example shows directly using Coinbase CDP API keys (apiKeyId/apiKeySecret). That is not intrinsically malicious, but it is a mismatch between declared requirements and the real-world need to supply payment credentials to the agent. Also, the SKILL.md hardcodes a pay-to address (0xd3c3...ccab) and a facilitator endpoint (api.cdp.coinbase.com); calling the service will cause micro-payments to that address — ensure you trust it before enabling automatic agent calls.
Persistence & Privilege
Skill is not always-on and does not request persistent system privileges. Autonomous invocation is allowed by default (normal), but nothing in the skill requests system-wide config changes or cross-skill credential access.
What to consider before installing
This skill calls an external API that charges small USDC payments per request; the payments are handled client-side via x402 and may require Coinbase CDP credentials or a wallet. Before installing: 1) Verify you trust api.aitrencher.xyz and the hardcoded pay-to address (0xd3c3...ccab). 2) Do NOT give your agent high-privilege Coinbase API keys unless you understand and limit their scope — prefer a dedicated low-balance wallet or restricted API key for testing. 3) Ensure your agent only makes requests when you explicitly authorize them (or disable automatic invocation), so it cannot make uncontrolled micro-payments. 4) Test with a tiny amount first and monitor transactions on Base. 5) If you need provenance, request the skill owner/source code or a homepage before using it with real funds.

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

latestvk97e4h1kqm8crzjjyz2tam0n2d84a66e
102downloads
0stars
2versions
Updated 3w ago
v1.0.1
MIT-0

TrencherAI — Base Chain Token Intelligence

TrencherAI is an AI-powered token scoring system for Base chain. It monitors Clanker, Bankr, and Doppler launches in real-time and scores them using a Claude Haiku reasoning pipeline with smart money tracking and pattern learning.

Payment

All endpoints use x402 micropayments (USDC on Base). No API key required. Your agent pays per request automatically if you have an x402-compatible client.

No credentials required on TrencherAI's side. Payment is handled entirely client-side by your x402-compatible agent using its own wallet. TrencherAI does not store, request, or have access to any client credentials.


Endpoints

1. Score a Token — $0.05 USDC

Analyze any Base chain token and get a 0-100 AI score with recommendation.

GET https://api.aitrencher.xyz/api/score-token?address={contract_address}

Parameters:

  • address (required): Base chain ERC-20 contract address (0x + 40 hex chars)

Example:

GET https://api.aitrencher.xyz/api/score-token?address=0x4ed4e862860bed51a9570b96d89af5e1b0efefed

Response (after x402 payment):

{
  "score": 82,
  "recommendation": "BUY",
  "smart_money": true,
  "pattern_win_rate": 0.73,
  "launchpad": "Clanker",
  "reasoning": "Strong smart money entry with high pattern confidence"
}

Response fields:

FieldTypeDescription
scoreinteger 0-100AI confidence score. 80+ = strong signal, 65-79 = moderate, <65 = weak
recommendationstringBUY, WATCH, or SKIP
smart_moneybooleanWhether tracked smart money wallets are buying this token
pattern_win_ratefloatHistorical win rate of similar token patterns (0.0-1.0)
launchpadstringToken origin: Clanker, Bankr, Doppler, or Base
reasoningstringOne-line AI explanation of the score

2. Hot Tokens Feed — $0.02 USDC

Get the top scoring Base chain tokens detected in the last N hours.

GET https://api.aitrencher.xyz/api/hot-tokens?limit={limit}&min_score={min_score}&hours={hours}

Parameters:

  • limit (optional, default 10): Number of tokens to return (max 50)
  • min_score (optional, default 70): Minimum score threshold
  • hours (optional, default 24): Lookback window in hours

Example:

GET https://api.aitrencher.xyz/api/hot-tokens?limit=5&min_score=80&hours=12

Response:

[
  {
    "symbol": "DEGEN",
    "address": "0x4ed4e862860bed51a9570b96d89af5e1b0efefed",
    "score": 95,
    "recommendation": "BUY",
    "launchpad": "Clanker",
    "has_smart_money": true,
    "alerted_at": "2026-04-05T14:30:00.000Z",
    "mcap": 45000
  }
]

3. Smart Money Activity — $0.10 USDC

Track smart money wallet movements on Base chain memecoins.

GET https://api.aitrencher.xyz/api/smart-money/activity?hours={hours}&limit={limit}

Parameters:

  • hours (optional, default 24): Lookback window in hours
  • limit (optional, default 20): Number of results (max 50)

Example:

GET https://api.aitrencher.xyz/api/smart-money/activity?hours=12&limit=10

Response:

[
  {
    "symbol": "AGENT",
    "address": "0x...",
    "score": 88,
    "launchpad": "Doppler",
    "detected_at": "2026-04-05T15:00:00.000Z",
    "signal": "ACCUMULATION"
  }
]

x402 Payment Flow

When your agent calls any endpoint, the server returns HTTP 402 with payment instructions:

{
  "x402Version": 1,
  "accepts": [{
    "scheme": "exact",
    "network": "eip155:8453",
    "amount": "50000",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "payTo": "0xd3c3b0b35a9252f438ac3c86ca0ce18caa02ccab",
    "maxTimeoutSeconds": 60
  }]
}

Your x402 client handles payment automatically. Example using Coinbase CDP:

Note: apiKeyId and apiKeySecret in the example below are your own Coinbase CDP credentials, used by your agent to sign payments client-side. TrencherAI never receives, requests, or stores any credentials — all signing happens locally in your agent.

import { createCdpAuthHeaders } from '@coinbase/x402';

const headers = createCdpAuthHeaders(apiKeyId, apiKeySecret);
const authHeaders = await headers();

const response = await fetch(
  'https://api.aitrencher.xyz/api/score-token?address=0x...',
  { headers: authHeaders.verify }
);

Use Cases

  • Token screening: Score newly launched tokens before buying
  • Portfolio monitoring: Track scores of tokens you hold
  • Smart money following: See what tracked wallets are accumulating
  • Market scanning: Find the highest-scored tokens in the last 24h
  • Automated trading: Use scores in your trading bot's decision pipeline

Scoring Methodology

TrencherAI scores tokens 0-100 using multiple signals:

SignalWeightSource
Smart Money EntryHighOn-chain wallet tracking via BaseScan
Telegram MentionsMediumReal-time group monitoring (50+ groups)
X/Twitter SentimentMediumPost volume and sentiment analysis
Deployer ReputationMediumHistorical deployer success rate
Pattern Win RateHighML pattern matching against 1800+ outcomes
Liquidity DepthLowPool analysis via DexScreener
Launchpad TrustBaseClanker/Bankr/Doppler = trusted LP lock

Score interpretation:

  • 90-100: Exceptional confluence of signals. Rare (<5% of tokens).
  • 80-89: Strong signal. Smart money + social proof present.
  • 65-79: Moderate signal. Some positive indicators.
  • <65: Weak or no signal. High risk.

Links

Comments

Loading comments...