Back to skill

Security audit

gemini-video-understanding

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for analyzing user-provided videos with Google Gemini, with the main caution that video content is sent to Google for processing.

Install only if you are comfortable sending the videos or public YouTube URLs you analyze to Google Gemini. Avoid private, regulated, confidential, or third-party media unless you have authorization and understand the provider's retention and privacy terms.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill clearly instructs users to upload local video files and submit YouTube URLs to Google's Gemini API, but it does not prominently warn that this content is transmitted to an external third-party service for processing. This can cause inadvertent disclosure of sensitive or regulated media, especially because videos may contain faces, voices, screens, documents, location data, or other embedded personal/confidential information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.