ClawHub
Back to skill

Security audit

gemini-count-in-video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for uploading videos to Google Gemini for object counting, with a privacy caution for surveillance footage.

Install only if you are comfortable sending the selected videos to Google Gemini for processing. For surveillance or workplace footage, confirm consent, legal basis, retention/data-use policy, and organizational approval, and consider redaction or anonymization before upload.

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
  • 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
95% confidence
Finding

The skill repeatedly instructs users to upload surveillance footage to Google's Gemini API but does not warn that these videos may contain sensitive personal data, regulated data, or confidential operational information being sent to a third-party service. In a surveillance context, the omission is more serious because footage commonly includes bystanders, employees, license plates, locations, and timestamps, creating privacy, compliance, and data-governance risk if users transmit data without informed consent or approval.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.