ClawHub
Back to skill

Security audit

BTC Bottom Signals

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently provides BTC market analysis through a disclosed AgentKey data connection, with no evidence of hidden, destructive, or unrelated behavior.

Before installing, be aware that relevant crypto-analysis requests can contact AgentKey and may require OAuth or an AgentKey API key. Avoid using it in conversations containing unrelated sensitive information unless you are comfortable with that third-party data path.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill enables implicit invocation globally without any visible trigger constraints, allowlist conditions, or user-confirmation requirements. That increases the chance the agent will automatically call the external MCP service in contexts the user did not explicitly intend, which can lead to unnecessary data sharing and unreviewed tool use.

External Transmission

Medium
Category
Data Exfiltration
Content
value: "agentkey"
      description: "AgentKey MCP for live crypto market, sentiment, and on-chain data"
      transport: "streamable_http"
      url: "https://api.agentkey.app/v1/mcp"
policy:
  allow_implicit_invocation: true
Confidence
83% confidence
Finding
The skill is configured to send data to an external HTTPS MCP endpoint, which creates a real outbound data-transmission path. In combination with implicit invocation, the agent may transmit prompts or derived user context to a third-party service without sufficiently explicit consent or minimization, creating privacy and supply-chain risk if the service is compromised or over-collects data.

Static analysis

No suspicious patterns detected.