ClawHub
Back to skill

Security audit

Take The Wheel

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes the conversation style so the agent asks guiding questions, with no evidence of hidden code, data access, persistence, or unsafe behavior.

Before installing, consider whether you want generic phrases like "guide me" to activate this mode. If that would be annoying, use the more specific "take the wheel" trigger or adjust the trigger wording where possible.

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 trigger phrases include broad, natural-language activations such as "guide me" and "ask me the questions," which are likely to appear in ordinary user conversations outside the intended context. This can cause accidental invocation of the skill and unexpected takeover of the interaction flow, increasing the risk of prompt-routing mistakes or misuse in sensitive tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.