ClawHub
Back to skill

Security audit

Cross-Exchange Arbitrage Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed public crypto price checker that fetches unauthenticated exchange ticker data and does not trade, collect credentials, or persist itself.

Install only if you are comfortable with the agent making live unauthenticated requests to Coinbase, Kraken, Bitstamp, Gemini, and OKX for the symbols you ask it to check. Treat results as gross price signals, not trading advice, because the skill does not account for fees, transfer time, or order-book depth.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill explicitly instructs the agent to run a Python script that fetches live public quotes from multiple exchanges, which requires network access, but the manifest declares no tool scope or permissions for that capability. This creates a governance and safety gap: an executor may allow undeclared outbound network activity, or reviewers/users may not realize the skill can reach external services and process untrusted remote data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/arb_scanner.py (reported line 41)May include surrounding context.

python
def fetch_coinbase(symbol: str):
    try:
        d = _get_json(f"https://api.exchange.coinbase.com/products/{symbol}-USD/ticker")
        return {"bid": float(d["bid"]), "ask": float(d["ask"])}
    except Exception:
        return None

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/arb_scanner.py (reported line 51)May include surrounding context.

python
pair_map = {"BTC": "XBTUSD", "DOGE": "XDGUSD"}
    pair = pair_map.get(symbol, f"{symbol}USD")
    try:
        d = _get_json(f"https://api.kraken.com/0/public/Ticker?pair={pair}")
        if d.get("error"):
            return None
        result = next(iter(d["result"].values()))

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/arb_scanner.py (reported line 70)May include surrounding context.

python
def fetch_gemini(symbol: str):
    try:
        d = _get_json(f"https://api.gemini.com/v1/pubticker/{symbol.lower()}usd")
        return {"bid": float(d["bid"]), "ask": float(d["ask"])}
    except Exception:
        return None