ClawHub
Back to skill

Security audit

Whale Watcher

Security checks for vulnerabilities and agentic risk

Overview

This is a simple crypto wallet transaction lookup skill with overstated alerting claims, but no hidden persistence, destructive behavior, or credential theft in the inspected artifacts.

Install only if you are comfortable sharing monitored wallet addresses and block explorer API keys with Etherscan or BscScan. Treat the advertised real-time Telegram alerts, paid-tier features, and broader chain support as not implemented in the inspected version.

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 (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The code is broadly related to whale-wallet transaction inspection, so the core theme matches the description. However, the declared description promises monitoring across Ethereum, BSC, and other chains, plus alerts when whales move significant amounts. In practice, the code only supports ETH and BSC, fetches recent transactions on demand, and prints findings locally. There is no scheduler, event listener, webhook, notification, or other alerting behavior. Thus the description overstates the implemented capabilities in material ways.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README encourages configuring Telegram and block explorer API keys and advertises real-time push notifications, but it does not warn users that monitored wallet addresses, transaction activity, and alert metadata may be transmitted to third-party services. In a crypto-monitoring context, this can expose sensitive trading interests or surveillance targets to external providers, creating privacy and operational security risks even if no direct code exploit is shown in the README.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The pricing descriptions and feature list are presented in Chinese, while the rest of the skill documentation is primarily in English. This creates an implicit language constraint for part of the user-facing content without opt-in or justification, which matches the language/locale policy violation criteria.

External Transmission

Medium
Category
Data Exfiltration
Content
from datetime import datetime

# API Keys (free tier)
ETHERSCAN_API = "https://api.etherscan.io/api"
BSCSCAN_API = "https://api.bscscan.com/api"

# Default free API keys (rate limited)
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
# API Keys (free tier)
ETHERSCAN_API = "https://api.etherscan.io/api"
BSCSCAN_API = "https://api.bscscan.com/api"

# Default free API keys (rate limited)
DEFAULT_ETHERSCAN_KEY = "YourApiKeyToken"
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
Several user-facing messages are hard-coded in Chinese, including status, threshold, error, and result output. This can violate a language/locale policy when the skill does not provide any user opt-in or alternative locale selection.

Natural-Language Policy Violations

Low
Confidence
97% confidence
Finding
The skill documentation forces a specific language context for core instructions and usage details, which can violate language/locale policy when no user opt-in or alternative is provided. There is no indication that the skill is intentionally region-specific or that other language options are available.

Static analysis

No suspicious patterns detected.