Back to skill

Security audit

跨市场交易终端

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only finance skill is not malicious, but it asks agents to support automated crypto trading and API-key workflows without clear safeguards or user approval gates.

Review carefully before installing. Treat this as a high-risk trading assistant: do not provide live exchange or broker credentials unless you understand the permissions, prefer read-only or paper-trading keys, and require explicit human approval for every account-linked action or trade.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation description is extremely broad and vague, telling the agent to use the skill whenever users need related functionality without meaningful scope limits. In a skill that exposes read and exec tools and claims trading capabilities, this can cause inappropriate invocation for sensitive financial actions or adjacent requests the skill is not safely designed to handle.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The markdown advertises automated arbitrage and automatic trading behavior but does not provide prominent warnings about financial loss, account risk, or the fact that autonomous actions may place real trades. In the context of a crypto trading skill, this increases the chance that an agent or user treats analysis output as permission for live execution, leading to direct monetary loss or unintended orders.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The setup steps tell users to configure API keys, initialize connections, and execute API calls, but they omit warnings about secret handling, least-privilege permissions, and the danger of using withdrawal or trading-enabled credentials. For a finance skill with execution capability, this creates a realistic path to credential exposure, account misuse, or accidental live trades.

Content

No source excerpt is available for this finding.