ClawHub
Back to skill

Security audit

ConsortiumAI Create Account

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it creates a Consortium AI custodial wallet account through a disclosed external API, with no hidden persistence or unrelated local access found.

Install only if you intend to create Consortium AI custodial wallet accounts and trust Consortium AI with the provided wallet address and API key. Use a dedicated, scoped API key if available, and verify account/custody terms before using it with real funds or production users.

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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill requires environment access for `TRADING_ANALYSIS_API_KEY` and network access to an external API, but it does not declare any explicit tool scope such as permissions or allowed tools. This weakens review and runtime policy enforcement, making it easier for an agent or user to invoke external account-creation behavior without clear consent boundaries.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill initiates creation of custodial wallet accounts through a third-party API but does not present a clear user-facing warning about the external action, custodial nature, or data-sharing implications. In a crypto context, account creation can have legal, privacy, and asset-control consequences, so omitting a warning increases the risk of uninformed or unintended use.

External Transmission

Medium
Category
Data Exfiltration
Content
**Backend API base URL:** `https://api.consortiumai.org`

**Endpoint:** `POST https://api.consortiumai.org/api/custodial-wallet/create-with-api-key`
Creates a new custodial wallet account.

### Authentication
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
**Backend API base URL:** `https://api.consortiumai.org`

**Endpoint:** `POST https://api.consortiumai.org/api/custodial-wallet/create-with-api-key`
Creates a new custodial wallet account.

### Authentication
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Intent-Code Divergence

Medium
Confidence
89% confidence
Finding
The script for creating Consortium AI custodial wallet accounts uses an environment variable named TRADING_ANALYSIS_API_KEY, which does not match the stated purpose or target service. This credential/documentation drift is dangerous because it can cause operators to supply an unrelated, over-privileged, or reused secret, increasing the chance of accidental credential exposure or misuse across systems.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/create-account.js:10