ClawHub
Back to skill

Security audit

跨境电商资讯日报

Security checks for vulnerabilities and agentic risk

Overview

This skill is a public cross-border ecommerce news brief generator with some overbroad routing language but no hidden code, persistence, credentials, or destructive behavior.

Installers should expect this skill to browse public ecommerce news sources and produce Chinese markdown briefings. Consider narrowing its trigger behavior if ambiguous ecommerce mentions should not automatically cause external news fetching.

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
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions are explicitly overbroad: the skill claims it should fire for very generic phrases like “跨境电商”, “出海资讯”, and even warns “不要 undertrigger,” which pressures the agent to invoke it without clear user intent. This can cause inappropriate routing, unnecessary external fetching, and displacement of better-suited skills or direct answers, especially when the user’s request is ambiguous.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description mandates Chinese output (“整理成中文 markdown 简报”) without considering the user’s language preference. This can lead to instruction conflict, poor usability, and incorrect behavior when the user asks in another language or expects locale-appropriate output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.