ClawHub
Back to skill

Security audit

跨境物流方案台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple logistics-advice skill with no code or privileged access, though its trigger examples are a bit broad.

Before installing, note that this skill gives planning guidance rather than guaranteed carrier quotes, customs rulings, or tax rates. Confirm time-sensitive prices, restrictions, certifications, and import duties with official sources or the carrier, especially for batteries, liquids, branded goods, or restricted products.

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
  • 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
92% confidence
Finding

The trigger keywords include broad, generic phrases such as “发德国”, “海运还是空运”, and “运费怎么算” that are likely to appear in ordinary user conversation outside an explicit request to invoke this skill. This can cause accidental activation or routing hijacks, making the assistant apply this skill in contexts where the user did not intend it, potentially producing logistics/compliance guidance on incomplete or inappropriate inputs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language examples are open-ended and include generic follow-up phrases like “按上面的结果改成更简短的版本” and “把这些整理成一张表”, which are common editing requests not uniquely tied to this skill. This increases the risk that normal conversational edits are misinterpreted as skill activation or continuation, leading to unintended use of the skill and incorrect handling of unrelated content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.