ClawHub
Back to skill

Security audit

First Customers

Security checks for vulnerabilities and agentic risk

Overview

This is a simple advice-only sales coaching skill for finding early customers, with no code execution, persistence, credential access, or hidden behavior.

Install this if you want focused guidance on finding your first customers. Be aware that it may activate for broad sales questions, so users may need to clarify when they want general sales advice rather than early-stage customer acquisition coaching.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger keywords include broad phrases like '找客户' and '怎么销售', which are common, everyday queries that can match many unrelated user requests. This can cause unintended invocation of the skill, leading the agent to apply narrow early-stage sales guidance in contexts where it is not appropriate, reducing reliability and potentially steering users off-topic.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.