ClawHub
Back to skill

Security audit

GPTChart - Analyse Trading Charts With AI

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to do what it says: send chart-analysis requests to GPTChart.ai with the user's API key, which may use account credits.

Install this only if you intend to send chart symbols and any custom trading prompts or strategy IDs to GPTChart.ai and accept that analysis calls may consume credits on the account tied to GPTCHART_API_KEY. Avoid putting secrets or proprietary trading logic into customPrompt unless you are comfortable sharing it with that service.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
When the user asks to analyze a symbol, construct a basic request:

```bash
curl -s -X POST https://gptchart.ai/api/v2/crypto/analyze \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GPTCHART_API_KEY" \
  -d '{
Confidence
93% confidence
Finding
This skill is designed to exfiltrate user-provided analysis inputs to an external service by making HTTPS POST requests to GPTChart.ai with the user's API key. In context this is expected functionality, but it still creates a real data-transfer boundary: symbols, custom prompts, strategy IDs, and other request content are disclosed to a third party, and the call can also spend the user's paid credits.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill clearly instructs the agent to send user-supplied trading symbols, prompts, strategy IDs, and related analysis parameters to GPTChart.ai using the user's API key, but the description does not prominently disclose that these inputs are transmitted to a third-party service. This is primarily a transparency and privacy issue: users may not realize their chart requests, custom prompts, or strategy identifiers leave the local agent environment.

Static analysis

No suspicious patterns detected.