ClawHub
Back to skill

Security audit

Chaos pivot

Security checks for vulnerabilities and agentic risk

Overview

This is a plain instruction-only troubleshooting skill that may activate broadly, but it does not request sensitive access, persistence, credentials, network use, or code execution.

Install this if you want the agent to use a structured pivot process when it gets stuck. Be aware that its trigger language is broad, so it may take over the agent's workflow during ordinary uncertainty or longer tasks, but no sensitive access or hidden execution behavior was found.

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
Confidence
95% confidence
Finding
The trigger is defined as 'ANY' of several broad conditions such as being 'stuck,' expressing uncertainty, or exceeding a vaguely defined expected step threshold. These conditions overlap with common agent behavior and do not provide concrete boundaries or negative examples, which could cause unintended invocation of the skill.

Static analysis

No suspicious patterns detected.