img2-generate-only

Security checks across malware telemetry and agentic risk

Overview

The skill is narrowly focused on image generation, but it hands an API key to a hard-coded local script that is not included in the package for review.

Review or obtain the referenced Python script before using this skill. Only provide a real API key after confirming both the script and base_url are trusted, and prefer environment variables or a secret store over command-line API-key arguments.

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: 84% confidence
Finding: The skill explicitly instructs users to provide a user-controlled base_url and api_key, and says prompts will be sent to that remote endpoint, but it does not warn that prompts and credentials are disclosed to whatever service is configured. In this context, the endpoint is fully user-supplied and the skill writes returned data locally, so the main risk is unintended data disclosure, use of untrusted providers, and integrity issues from relying on arbitrary remote image content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal