ClawHub
Back to skill

Security audit

Use Cases

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only guidance skill about AI use cases, with no code execution or privileged behavior, though one beginner privacy reassurance is too broad.

Safe to install as a general AI-use-case guide. Users should still follow their product and workplace privacy policies and avoid entering passwords, API keys, confidential business data, personal records, financial details, medical information, or legal secrets unless they understand the tool's data handling terms.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation guidance says the skill is for someone asking "what can this actually do?" and then to identify their context, but it does not define a narrow trigger boundary or exclusions. This is broad, everyday phrasing that could overlap with many generic help or discovery requests and cause unintended invocation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The file gives a broad privacy reassurance by saying conversations aren't shared with others, while only narrowly cautioning against pasting passwords. That can mislead beginners into sharing other sensitive personal, financial, medical, legal, or confidential business information under a false sense of safety, especially because this skill explicitly targets new users who may not understand data handling limits.

Static analysis

No suspicious patterns detected.