ClawHub
Back to skill

Security audit

Content Type Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed content-classification helper with an optional database-backed configuration mode, and I did not find hidden execution or unsafe behavior.

Before installing, confirm whether you intend to use the optional Supabase-backed mode. If not, leave DB mode disabled; if yes, review the backing table and credentials because database-loaded content type rules can influence downstream image prompts.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest describes a router that detects and classifies visual content types from text descriptions or hints. However, the documentation exposes an additional capability to load brand-specific overrides from a Supabase table and toggle DB mode at runtime, which introduces external data access/stateful behavior not obviously required for a local classification skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.