ClawHub
Back to skill

Security audit

Hobbes

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Thomas Hobbes roleplay skill with no tool access, code execution, persistence, or data access.

Install this if you want a Hobbes-style conversational persona. Be aware that simply mentioning "hobbes" may activate it; using explicit triggers like /hobbes is clearer.

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
95% confidence
Finding

The standalone trigger "hobbes" is broad enough to match ordinary user text that mentions Hobbes rather than intentionally invoking the skill. This can cause unintended activation and persona hijacking of unrelated conversations, especially because it is a common proper noun in educational or philosophical contexts.

Content

No source excerpt is available for this finding.