ClawHub
Back to skill

Security audit

CoinGecko

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches cryptocurrency market information from CoinGecko and does not show hidden, persistent, destructive, or credential-seeking behavior.

Before installing, understand that crypto search terms and token addresses you ask about will be sent to CoinGecko. The skill appears appropriate for market lookups and does not show evidence of local data access, persistence, or account-changing authority.

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 consistent with part of the description: it calls the CoinGecko API and returns current price and market data for specified coins. However, the declared description is broader than the actual implementation. The script only supports querying the /coins/markets endpoint for provided CoinGecko coin IDs via CLI arguments. It does not include functionality for trending coins, token searches/lookups by symbol or name, or Solana contract-address-based lookups. This is a description-to-behavior mismatch because several advertised capabilities are not present in the supplied code chunk.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The code accesses CoinGecko, which is consistent with the declared resource, but its implemented functionality is much narrower than the description. It calls only the /search endpoint and outputs basic match metadata. There is no logic for price retrieval, broader market data, trending coins, or contract-address-based Solana token lookup. Therefore the declared description materially overstates the skill’s actual behavior.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The declared description presents a general-purpose CoinGecko skill for crypto prices, market caps, 24h changes, trending coins, and token lookups. The supplied code is much narrower: it calls only the CoinGecko /coins/{platform}/contract/{address} endpoint and formats the returned token's market fields. It does align with the specific claim about Solana token lookups by contract address, and it does use CoinGecko as described. However, it does not support the broader advertised capabilities such as generic BTC/ETH/SOL price queries, trending coins, or general coin/token lookup by name or symbol. Therefore the description overstates the implemented functionality in a materially significant way.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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/price.py (reported line 11)May include surrounding context.

python
import json, urllib.request, urllib.error

def main():
    url = "https://api.coingecko.com/api/v3/search/trending"
    req = urllib.request.Request(url, headers={"Accept": "application/json", "User-Agent": "openclaw-coingecko/1.0"})
    try:
        with urllib.request.urlopen(req, timeout=15) as resp:

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/search.py (reported line 11)May include surrounding context.

python
import json, urllib.request, urllib.error

def main():
    url = "https://api.coingecko.com/api/v3/search/trending"
    req = urllib.request.Request(url, headers={"Accept": "application/json", "User-Agent": "openclaw-coingecko/1.0"})
    try:
        with urllib.request.urlopen(req, timeout=15) as resp:

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/token.py (reported line 15)May include surrounding context.

python
import json, urllib.request, urllib.error

def main():
    url = "https://api.coingecko.com/api/v3/search/trending"
    req = urllib.request.Request(url, headers={"Accept": "application/json", "User-Agent": "openclaw-coingecko/1.0"})
    try:
        with urllib.request.urlopen(req, timeout=15) as resp:

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/trending.py (reported line 6)May include surrounding context.

python
import json, urllib.request, urllib.error

def main():
    url = "https://api.coingecko.com/api/v3/search/trending"
    req = urllib.request.Request(url, headers={"Accept": "application/json", "User-Agent": "openclaw-coingecko/1.0"})
    try:
        with urllib.request.urlopen(req, timeout=15) as resp:

Static analysis

No suspicious patterns detected.