ClawHub
Back to skill

Security audit

Internet

Security checks for vulnerabilities and agentic risk

Overview

This is a static internet-help guide that gives proportionate troubleshooting and shopping advice without hidden execution or persistence.

Installers should treat this as an advisory troubleshooting skill. Be careful before sharing precise addresses, account numbers, router admin access, or making provider/eSIM purchases, but the artifacts themselves do not request hidden access or automatic changes.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Common Traps

- Recommending provider switch without checking contract end date → user pays penalty
- Assuming WiFi issue when it's ISP problem → wasted troubleshooting
- eSIM purchase without verifying phone support → money lost
- QoS advice without knowing router model → unusable instructions
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.