Back to skill

Security audit

外贸业务全能助手

Security checks for vulnerabilities and agentic risk

Overview

This is a static foreign-trade template and guidance skill with no code execution, persistence, credential access, or hidden data handling.

Before installing, treat the contract, customs, logistics, and dispute content as general drafting support only. Users should verify legal, customs, tax, and shipment decisions with qualified professionals or authoritative sources before relying on them in real transactions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is very broad, covering many common foreign-trade tasks such as outreach, quotations, contracts, logistics, and disputes. Because activation scope is not tightly bounded, an agent may invoke this skill for a wide range of routine business requests, increasing the chance of unintended triggering, response hijacking, or bypass of more appropriate specialized safeguards.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow says the skill should act 'when foreign trade practitioners need help,' which is ambiguous and effectively applies to almost any trade-related request. This broad trigger can cause over-activation, making the system more likely to route unrelated or higher-risk requests into this skill without sufficient contextual checks.

Content

No source excerpt is available for this finding.