ClawHub
Back to skill

Security audit

Mock Trading

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed paper-trading skill that fetches public crypto prices and updates a local mock portfolio, with no evidence of real trading, credential use, exfiltration, or hidden behavior.

Install only if you are comfortable with a mock trading script contacting CoinGecko for price data and modifying a local portfolio JSON file. Do not enable HEARTBEAT.md or cron automation unless you intentionally want it to run repeatedly, and remember that this is paper trading only, not financial advice or real exchange trading.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill description promises paper trading behavior but omits that it fetches live external market data and overstates implemented strategy support. This mismatch can mislead users and reviewers about both the skill's network behavior and its functional limits, causing unapproved data egress and incorrect trust in how the bot operates.

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to run code that reads and writes local files and performs network access, but it declares no explicit tool scope or permissions. That omission weakens reviewability and consent boundaries, making it easier for an agent to perform side effects the user or platform did not clearly authorize.

External Transmission

Medium
Category
Data Exfiltration
Content
import os

def get_crypto_price(asset_id="bitcoin"):
    url = f"https://api.coingecko.com/api/v3/simple/price?ids={asset_id}&vs_currencies=usd"
    response = requests.get(url)
    data = response.json()
    return data[asset_id]["usd"]
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The code writes the portfolio JSON back to disk, replacing the existing file contents, but there is no comment, docstring, or user-facing warning near the write operation explaining that the file will be modified. Although trade actions are printed, the persistence step itself is silent and can alter user data on every run.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill tells the agent to copy a template portfolio and later update that local file, but it does not warn the user that local files will be created and modified. Even though this is a mock trading context, silent file writes and especially persistence via HEARTBEAT.md or cron can create unintended state changes and surprise automation on the user's system.

Static analysis

No suspicious patterns detected.