ClawHub
Back to skill

Security audit

AURUM Gallery

Security checks for vulnerabilities and agentic risk

Overview

This gallery skill has a coherent purpose, but the package is incomplete and gives overly broad instructions for actions against a shared external gallery.

Review this carefully before installing. The intended gallery functions are normal for a shared art collection, but the package does not include the scripts or setup files it tells agents to run, and its activation wording is too broad. Only use it if you are comfortable configuring Supabase yourself and ensuring uploads, likes, and data fetches happen only after clear user intent.

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
96% confidence
Finding
The trigger scope is overly broad because it activates on essentially any mention of the AURUM gallery or AI art collection, rather than on clear user intent to perform a gallery action. This can cause the agent to invoke the skill in contexts where the user is only discussing the gallery, increasing the chance of unintended external actions or unnecessary data access.

Static analysis

No suspicious patterns detected.