ClawHub
Back to skill

Security audit

生意人防坑顾问

Security checks for vulnerabilities and agentic risk

Overview

This is a content-only business deal review skill with no code execution, persistence, or hidden data access.

Before installing, understand that this skill is meant for practical business-risk review of text you choose to paste. Avoid sharing unnecessary personal or confidential details, and use a lawyer for large, complex, or legally sensitive agreements.

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
Confidence
95% confidence
Finding
The description includes broad activation examples such as users saying they want help reviewing a cooperation or contract and pasting messages, without strong exclusion criteria. That can cause the skill to trigger on loosely related business or negotiation content, leading to unintended handling of sensitive user material and incorrect routing away from more appropriate skills.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list contains short, ambiguous phrases that do not require enough context to distinguish this skill from generic business-advice scenarios. In a content skill that invites users to paste contracts and chat logs, overbroad triggering raises the chance of accidental invocation on unrelated conversations containing sensitive commercial details.

Static analysis

No suspicious patterns detected.