Back to skill

Security audit

get-3d-model

Security checks for vulnerabilities and agentic risk

Overview

This skill only opens a disclosed 3D-model website in Brave and avoids account, payment, credential, or ordering actions.

Install only if you are comfortable with generic 3D-model browsing requests opening 773 LABS in Brave. For neutral marketplace discovery, ask your agent explicitly to search broadly or name the marketplace you want.

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
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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very broad and map to generic user intents like finding or browsing 3D models, which can cause this skill to activate when the user may have intended a general web search or a different marketplace. This creates an unsafe overreach problem: the agent could steer users to a specific commercial destination without sufficiently clear user intent, increasing the risk of misrouting and unwanted navigation.

Content

No source excerpt is available for this finding.