LIVE ORACLE // 5 CHAINS // LLAMA 3.3 70B

VOIDSCANNER

AI-powered bytecode risk oracle for EVM smart contracts.
Detect honeypots, rug vectors, and exploit patterns before you sign.

Ethereum · Base · Arbitrum · Polygon · Optimism

14 exploit signatures · Llama 3.3 70B · < 4s full analysis · 24h cache

LIVE SCAN FEED
RISKYETH0x7a250d...42/10012s
SAFEETH0x3fC91A...8/10034s
SAFEBASE0x111111...12/1001m
ABORTARB0xC36442...89/1002m
RISKYPOLY0x68b346...55/1003m
14,291
CONTRACTS SCANNED
across all 5 chains
891
HONEYPOTS DETECTED
rugpulls neutralized
5
CHAINS SUPPORTED
EVM networks
3.8s
AVG RESPONSE TIME
full AI analysis
312
ABORT VERDICTS
transactions blocked
28.4K
API CALLS SERVED
programmatic scans
POWERED BY
GROQ
Llama 3.3 70B — < 2s inference
ETHERSCAN V2
Unified multi-chain bytecode API
TENDERLY
Transaction simulation engine
SUPABASE
24h analysis result cache
HEIMDALL-RS
EVM bytecode decompiler
4BYTE.DIRECTORY
Function selector resolution

HOW IT WORKS

FIVE STAGES FROM ADDRESS TO VERDICT

01
ENTER ADDRESS
< 1s

Paste any 0x contract address and select the chain. Works with unverified contracts — bytecode analysis doesn't need source code. The Oracle accepts any valid 40-char hex address deployed on any supported EVM network.

02
FETCH BYTECODE
~0.8s

VOID SCANNER pulls raw EVM bytecode from Etherscan V2 and checks whether the source is verified. If verified, the actual Solidity source is used for deeper pattern matching. A SHA-256 hash of the bytecode is computed for cache keying.

03
PATTERN SCAN
~0.2s

14 exploit signatures are matched against the bytecode and decompiled output with byte-aligned opcode parsing. PUSH operands are skipped during iteration to eliminate false positives from embedded data. Each match is classified LOW / MEDIUM / HIGH / CRITICAL and carries an exact bytecode offset.

04
AI ANALYSIS
~2s

Llama 3.3 70B reads the decompiled pseudo-Solidity, matched patterns, and up to 15 resolved function selectors to compute a risk score, honeypot probability (0–1), rug pull likelihood (0–1), and a plain-English verdict summary. Groq's inference delivers results in under 2 seconds.

05
VERDICT
~0.1s

Pattern severity weights are summed (CRITICAL=25, HIGH=15, MEDIUM=8, LOW=3) and blended with the AI score. The final 0–100 risk score maps to SAFE (0–30), RISKY (31–65), or ABORT (66–100). Results are cached in Supabase for 24 hours and returned as structured JSON.

CAPABILITIES

EVERY LAYER OF THE SECURITY STACK

BYTECODE ORACLE
CORE ENGINE

Pulls raw EVM bytecode directly from Etherscan V2 across 5 chains. Parses every opcode with byte-aligned disassembly — PUSH data is skipped so false positives are eliminated. Resolves function selectors via 4byte.directory to reconstruct method names from the ABI.

Etherscan V2 API (all chains)
Byte-aligned opcode parser
Function selector resolution
Source verification check
PATTERN MATCHING
14 EXPLOIT SIGNATURES

Hardcoded library of 14 known exploit patterns matched against both raw bytecode and decompiled Solidity output. Detects SELFDESTRUCT, DELEGATECALL, honeypot transfer blocks, unlimited approval drains, tx.origin auth, reentrancy vectors, and more.

SELFDESTRUCT / DELEGATECALL opcodes
Honeypot transfer blocking
Unlimited approval drain
Reentrancy + unchecked calls
AI DEEP SCAN
LLAMA 3.3 70B VIA GROQ

Every contract is sent to Llama 3.3 70B (via Groq's ultra-fast inference) for contextual security analysis. The model reads decompiled source, matched patterns, and function signatures to compute honeypot probability, rug pull likelihood, and write a plain-English verdict.

Honeypot probability score
Rug pull likelihood
Plain-English summary
Developer audit notes
PRE-SIGN SHIELD
CHROME EXTENSION

Manifest V3 extension that wraps window.ethereum via provider proxy injection. Intercepts eth_sendTransaction and eth_signTransaction before they reach MetaMask. Runs Oracle analysis + Tenderly simulation in parallel, then injects a full-screen verdict overlay blocking the tx.

Wraps window.ethereum
Parallel Oracle + simulation
Full-screen ABORT overlay
Auto-abort on ABORT verdict
MCP SERVER
AI AGENT INTEGRATION

Exposes the Oracle as a Model Context Protocol server at /api/mcp. AI agents (Claude, GPT-4, custom LLMs) can call analyse_contract, get_risk_score, and check_patterns as tools. Requires a PRO or ENTERPRISE API key passed as Bearer token.

3 MCP tool definitions
Bearer token auth
JSON schema validated
Works with any MCP client
MULTI-CHAIN
5 EVM NETWORKS

Supports Ethereum mainnet, Base, Arbitrum, Polygon, and Optimism — all via Etherscan V2's unified API endpoint. Each chain gets byte-accurate bytecode and source verification. Shareable scan URLs include chain context for one-click re-analysis.

Ethereum / Base / Arbitrum
Polygon / Optimism
Unified Etherscan V2 API
Chain-aware shareable URLs

EXPLOIT PATTERN LIBRARY

14 SIGNATURES MATCHED AGAINST EVERY CONTRACT

Each pattern is matched at the EVM opcode level using byte-aligned disassembly. PUSH operands are skipped during iteration to eliminate false positives from embedded data.

HIGH
SELFDESTRUCT
Contract can be destroyed, draining all funds permanently
HIGH
DELEGATECALL
Logic proxied to potentially attacker-controlled address
CRITICAL
HONEYPOT_TRANSFER
Transfer function has hard-coded revert — can't sell
HIGH
APPROVAL_DRAIN
Requests max uint256 approval — unlimited spend vector
MEDIUM
TX_ORIGIN_AUTH
tx.origin used for auth — phishing attack vulnerable
MEDIUM
HIDDEN_MINT
Owner can mint tokens at will — infinite dilution rug
HIGH
REENTRANCY_RISK
State modified after external call — classic reentrancy
HIGH
UNCHECKED_CALL
Low-level call return value not verified — silent failure
MEDIUM
PROXY_UPGRADE
Logic can be silently replaced post-deploy by owner
MEDIUM
FEE_ON_TRANSFER
Hidden tax on transfers — sell amount differs from expected
MEDIUM
BLOCKHASH_RANDOM
Blockhash used as randomness — manipulable by validators
CRITICAL
DELEGATECALL_STORAGE
Delegatecall reads caller storage — classic proxy exploit
LOW
HIDDEN_PAUSE
Owner can freeze all contract operations at will
HIGH
BLACKLIST_OWNER
Owner can blacklist addresses, preventing token transfers or sells
CRITICAL(2)
HIGH(6)
MEDIUM(5)
LOW(1)

PRICING

ONE PREVENTED RUG PULL PAYS FOR A YEAR

FREE
$0
10 queries
5 scans/hour
All 5 chains
Pattern matching (14 signatures)
AI analysis (Llama 3.3 70B)
24h result cache
Shareable scan URLs
SCAN FOR FREE
◈ MOST POPULAR
PRO
$19/mo
500 queries/mo
Unlimited rate
All 5 chains
API key access
Tenderly tx simulation
Priority analysis queue
Dashboard + usage stats
Bearer token auth
ENTERPRISE
$79/mo
Unlimited queries
Unlimited queries
MCP server access
Webhook alerts on ABORT
Custom pattern library
SLA support
White-label API
Dedicated analysis queue

All plans include AI analysis · Cancel anytime · Instant activation

FAQ

COMMON QUESTIONS ABOUT THE ORACLE

Q.
Does VOID SCANNER work on unverified contracts?

Yes — all 14 exploit pattern signatures operate at the EVM opcode level, so raw bytecode is all we need. No source code required. When source is verified on Etherscan, the AI receives deeper context for more nuanced scoring, but every pattern check works regardless of verification status.

Q.
How is the 0–100 risk score calculated?

Severity weights from matched patterns are summed: CRITICAL = 25 pts, HIGH = 15 pts, MEDIUM = 8 pts, LOW = 3 pts. The AI analysis can adjust the final score ±20 points based on contextual review of function selectors and decompiled logic. Score 0–30 → SAFE, 31–65 → RISKY, 66–100 → ABORT.

Q.
What's the difference between RISKY and ABORT?

RISKY (31–65) means suspicious patterns are present — investigate before interacting. ABORT (66–100) means confirmed exploit vectors: SELFDESTRUCT present, honeypot transfer blocking detected, or AI honeypot probability above 0.8. The Chrome extension automatically blocks ABORT transactions before they reach MetaMask.

Q.
How does the Chrome extension intercept transactions?

The Manifest V3 extension injects a provider proxy at window.ethereum that wraps eth_sendTransaction and eth_signTransaction. When you hit 'confirm' in any dApp, the proxy fires before MetaMask receives the call — running Oracle analysis and Tenderly simulation in parallel and rendering a full-screen verdict overlay.

Q.
Which chains are supported?

Ethereum mainnet, Base, Arbitrum, Polygon, and Optimism — all via Etherscan V2's unified API endpoint. Each chain returns byte-accurate bytecode and source verification status from the same authentication key. More chains (BSC, Avalanche) are planned.

Q.
Can AI agents and bots use VOID SCANNER?

Yes. ENTERPRISE plans include MCP server access at /api/mcp. AI agents like Claude or GPT-4 can call analyse_contract, get_risk_score, and check_patterns as structured tools. PRO plans get a standard REST API key (Bearer token) for direct programmatic integration.

INTEGRATE THE ORACLE

One POST request. Full analysis in under 5 seconds.
Works in any language. Returns structured JSON with flags, probabilities, and AI verdict.

curl -X POST https://xrvoid.online/api/analyse \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer vs_your_api_key" \
  -d '{"address":"0x...","chain":"ethereum"}'

# Response (< 5 seconds):
{
  "verdict": "ABORT",
  "riskScore": 89,
  "verified": false,
  "analysisTimeMs": 3241,
  "honeypotProbability": 0.94,
  "rugProbability": 0.31,
  "flags": [
    { "severity": "CRITICAL", "id": "HONEYPOT_TRANSFER",
      "title": "Honeypot Transfer Block",
      "description": "Transfer reverts for non-owner addresses" },
    { "severity": "HIGH", "id": "SELFDESTRUCT",
      "title": "Self-Destruct Vector",
      "bytecodeOffset": "0x1a4" }
  ],
  "patternsMatched": ["HONEYPOT_TRANSFER", "SELFDESTRUCT"],
  "aiExplanation": "Contract has hard-coded sell restriction...",
  "keyFindings": [
    "Transfer reverts for non-owner",
    "SELFDESTRUCT reachable by deployer",
    "No liquidity lock detected"
  ],
  "auditNotes": "Do not interact. Pattern consistent with honeypot.",
  "cached": false
}