ClawHub
Back to skill

Security audit

crypto briefing

Security checks for vulnerabilities and agentic risk

Overview

This skill gathers public crypto market and news data to produce a Chinese briefing, with no hidden persistence, credential theft, or destructive behavior found in the inspected artifacts.

Before installing, expect the skill to browse CoinMarketCap and several crypto news sites and, if the helper script is used, to call CoinGecko and alternative.me. Use a clean browser profile if you do not want existing cookies involved, and treat the generated trend predictions and strategy text as informational rather than financial advice.

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
96% confidence
Finding

The declared description promises a broader crypto market briefing capability including latest news, price analysis, trend predictions, sentiment analysis, and report generation for several assets. The supplied code does not implement those behaviors. It performs a narrow data-fetching task: retrieving spot prices/24h change for a fixed list of coins and the Fear & Greed Index, then outputting raw JSON. This is a materially different and much narrower behavior than the declared purpose. There is no undeclared sensitive capability, but the description overstates what the code actually does.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill instructs the agent to browse multiple external websites and fetch live market data, but it does not declare an explicit tool scope such as allowed network/browser permissions. That creates an overbroad capability boundary where a host system may permit network access implicitly, making review, sandboxing, and policy enforcement weaker.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The report template explicitly mandates Chinese output, including the title and timestamp label, and the rest of the template continues in Chinese. This is a natural-language locale policy issue because the skill does not provide opt-in, fallback, or any explanation that it is intended only for Chinese-language users or a region-specific workflow.

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/fetch_data.py (reported line 23)May include surrounding context.

python
def main():
    # Fetch prices
    coin_ids = "bitcoin,ethereum,solana,sui,worldcoin-wld,dogwifcoin"
    price_url = f"https://api.coingecko.com/api/v3/simple/price?ids={coin_ids}&vs_currencies=usd&include_24hr_change=true"
    
    prices = fetch_json(price_url)

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/fetch_data.py (reported line 28)May include surrounding context.

python
prices = fetch_json(price_url)
    
    # Fetch Fear & Greed Index
    fng_url = "https://api.alternative.me/fng/?limit=1"
    fng_data = fetch_json(fng_url)
    
    if not prices or not fng_data: