logo-generator

Security checks across malware telemetry and agentic risk

Overview

This is a simple logo guidance skill with no code execution or account access; its only notable behavior is reading local project context files if present.

Safe to install for logo implementation guidance. Keep project context files free of secrets or unrelated private data, because the skill may read them to tailor brand guidance.

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: 89% confidence
Finding: The skill description is overly broad and includes many generic logo- or branding-related phrases, which can cause the agent to invoke this skill in contexts where the user did not actually want logo placement or implementation guidance. This is primarily a scope/quality vulnerability rather than a direct exploit, but it can misroute user requests, suppress more appropriate skills, and increase the chance of irrelevant or misleading outputs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal