Back to skill

Security audit

外贸工厂询盘全流程 Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only trade inquiry assistant that drafts quotes, emails, and customer summaries without hidden execution or persistence.

Before installing, treat any generated customer profile as business-sensitive data: only include necessary contact details, confirm quotes and trade terms before sending, and avoid using the skill as a source of legal, tariff, or compliance advice without review.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger description is broad enough to activate on many ordinary trade or export-related conversations, which can cause the agent to engage outside a clearly intended scope. Over-broad activation increases the chance of inappropriate automation, unnecessary collection of business/customer data, or generation of authoritative trade guidance when the user did not explicitly request this specialized workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly supports customer record creation and follow-up tracking, which implies handling personal and business contact data, but it provides no privacy notice, retention rule, consent requirement, or restrictions on sensitive data handling. In a sales context this can lead to unnecessary storage or exposure of customer information and increases compliance risk under privacy and data-protection regimes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Line L03 explicitly specifies '标准报价单格式(中文抬头)', which imposes a Chinese-language format as the default instruction. Under the policy rules, forcing a specific language without user opt-in or a documented business/regional justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill specifies that quotations are generated in both Chinese and English, which imposes a language behavior by default. There is no indication that users can choose a preferred language or opt out of bilingual output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The document title and surrounding instructional content are written in Chinese, establishing a specific language expectation for use of the skill content. The file does not indicate that other languages are supported or that the user may opt into a preferred language, which can conflict with language-choice policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill reference content is written in Chinese, and there is no indication that users may choose another language or that the file is intentionally restricted to a Chinese-speaking or region-specific context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.