Back to skill

Security audit

gemini-delegation

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Gemini CLI delegation guide, but users should be mindful that file references may send local content to Gemini.

Install only if you intend to use Gemini CLI delegation. Before using @file or glob examples, confirm the selected files are appropriate to share with Google/Gemini and avoid broad globs over secrets, private repositories, or sensitive business data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list contains broad, generic terms such as "gemini," "cli," "delegation," and "google," which can cause the skill to activate in contexts unrelated to intentional delegation. Overbroad activation increases the chance that users or agents invoke this skill unexpectedly, which is risky here because the skill is designed to route prompts and file contents to an external CLI/service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The examples explicitly show passing local file contents to the Gemini CLI using patterns like "@path/to/file" and globbing multiple files, but the skill does not warn that this may disclose sensitive source code or data to an external model provider. In a delegation skill, that omission is materially dangerous because the skill normalizes remote transmission as a routine action without requiring user awareness or consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.