Back to skill

Security audit

Gemini

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Gemini connector wrapper that uses OOMOL's oo CLI and does not show hidden, destructive, or unrelated behavior.

Install this only if you are comfortable connecting Gemini through OOMOL and letting the agent run oo connector actions for Gemini tasks. Review any generated payloads for costly media generation, and verify the oo CLI installer source before running first-time setup commands.

SkillSpector

By NVIDIA
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
Confidence
92% confidence
Finding
The trigger phrase 'Use this skill for ANY Gemini request' is overly broad and can cause the agent to route many unrelated or insufficiently scoped tasks through this skill automatically. In an agent setting, broad routing language increases the chance of unintended tool invocation and expands the blast radius of any unsafe behavior elsewhere in the skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.