Back to skill

Security audit

open-kaggle

Security checks for vulnerabilities and agentic risk

Overview

This skill only opens Kaggle in Brave and has clear limits against handling credentials or changing account/content data.

Before installing, understand that invoking the skill can bring Brave to the foreground and open or reuse a Kaggle tab, including any existing signed-in browser session. It does not ask for or store credentials and instructs the agent to stop at login if sign-in is required.

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
94% confidence
Finding

The trigger description uses broad natural-language phrases such as 'open, visit, or go to Open Kaggle,' which can increase the chance of unintended invocation from ordinary conversation. While the skill only opens a website and includes scope limits, accidental activation could still cause unwanted browser focus/navigation and mild user confusion or disruption.

Content

No source excerpt is available for this finding.