ClawHub
Back to skill

Security audit

crypto-supply-dilution-tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward crypto supply analysis helper that makes disclosed CoinGecko API requests and does not show hidden persistence, credential access, or destructive behavior.

Before installing, understand that coin IDs or top-N scan choices will be sent to CoinGecko and that the output is a supply-side proxy, not investment advice or a vesting unlock calendar. A stricter package could declare an explicit network allowlist for CoinGecko, but the reviewed artifact behavior is disclosed and limited.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill documentation describes live calls to CoinGecko's public API, indicating network capability, but the skill declares no explicit tool scope such as permissions or allowed-tools. Undeclared network access weakens sandboxing and review controls because an agent may be allowed to make outbound requests beyond what operators expect, increasing the risk of data exfiltration, unexpected external dependencies, or abuse if the implementation changes.

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/dilution_tracker.py (reported line 31)May include surrounding context.

python
import urllib.request
import urllib.error

COINGECKO_MARKETS = "https://api.coingecko.com/api/v3/coins/markets"


def fetch_markets(ids=None, top=None):