ClawHub
Back to skill

Security audit

Content Type Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only content classification guide with no hidden execution, persistence, or unrelated data access.

Install this if you want agents to classify visual content requests into layout and generation categories. Review the optional database-mode examples only if your environment actually provides the referenced Python modules and Supabase table.

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

Low
Confidence
84% confidence
Finding
The description says to use the skill whenever you need to classify a content generation request into a structured type, but it does not define explicit trigger phrases, scope limits, or negative examples. For a markdown skill description, this can be overly broad and may cause the router to be invoked for a wide range of ordinary content-generation discussions.