Emmestudio Brand

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed EmmeStudio branding helper, with the main caution that it may apply branding broadly and may direct the agent to fetch templates from Google Drive.

Install this if you want EmmeStudio branding applied to documents and presentations. Before allowing Drive access, confirm the Google Drive folder and account are legitimate and that the current task actually needs the official templates or fonts.

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 (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill description is triggered by very common requests such as creating documents, presentations, letters, or any 'on-brand' output, without sufficiently constraining when it should apply. In an agent system, this can cause over-broad routing or unintended invocation, leading the model to pull in brand-specific instructions and external resources for unrelated tasks, increasing the risk of scope hijacking or accidental data exposure.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The activation rule applies to any output that represents EmmeStudio externally or any formal internal document, but it does not define boundaries for what qualifies as such content. This ambiguity can make the skill activate in many normal workflows, potentially overriding more appropriate skills or injecting branding workflow steps, including external Drive access instructions, into tasks that did not require them.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal