ClawHub
Back to skill

Security audit

Ask

Security checks for vulnerabilities and agentic risk

Overview

This is a simple reflective-questioning skill with no code, tools, persistence, credentials, or data access, though its activation description is broad.

Before installing, consider whether you want a broadly triggered coaching-style questioning framework. It appears low risk technically, but its broad scope may affect how often the agent responds with questions instead of direct answers.

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 description is very broad and can match a large share of normal user conversations, such as uncertainty, decisions, difficult conversations, or not knowing where to start. Over-broad activation can cause the skill to engage when it was not explicitly needed, increasing unintended prompt injection exposure, context hijacking, and inappropriate steering of benign conversations.

Static analysis

No suspicious patterns detected.