ClawHub
Back to skill

Security audit

Brand

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only brand strategy skill with no code execution, data access, persistence, or hidden behavior.

Installers should know this skill may be invoked for a wide range of branding or messaging conversations, but it is advisory content only and does not appear to access data, run commands, install components, or persist state.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger description is overly broad and can activate on many common branding or messaging conversations, causing the skill to be invoked when it may not be the best or safest fit. While this is not a code-execution issue, excessive scope increases the chance of unintended routing, irrelevant guidance, and interference with more specialized skills.

Session Persistence

Medium
Category
Rogue Agent
Content
},

  "voice_archetypes": {
    "The Expert":     "Authoritative, precise, evidence-based. Never simplistic.",
    "The Friend":     "Warm, direct, honest. Says what others think but do not say.",
    "The Rebel":      "Challenges conventions. Provocative but purposeful.",
    "The Guide":      "Patient, clear, empowering. Makes complex things accessible.",
Confidence
75% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.