gpt-multimodal

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward OpenAI image-analysis guide, but users should be mindful that selected images and visible text are sent to OpenAI when used.

Install only if you are comfortable sending chosen images, screenshots, frames, prompts, and any visible text in those images to OpenAI. Avoid using it on secrets, regulated records, private documents, or sensitive screenshots unless approved, and prefer a dedicated API key with usage limits.

SkillSpector

By NVIDIA

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

Confidence: 91% confidence
Finding: The skill repeatedly instructs users to send local images and video frames to the OpenAI API, but it does not clearly disclose the privacy and data-governance implications of transmitting potentially sensitive visual content off-system. This can lead to unintentional exposure of PII, confidential documents, screenshots, location data, or regulated data because users are not prompted to classify or minimize sensitive content before upload.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal