Security audit

Ai Image Generation

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward SkillBoss image-generation API guide with expected use of an API key and external prompt/image submission, but users should be aware of privacy implications.

Install only if you are comfortable sending image prompts, referenced image URLs, and related request metadata to SkillBoss. Use a dedicated, revocable SkillBoss_API_KEY and avoid submitting confidential prompts, private image links, or proprietary visual material unless SkillBoss's data handling terms are acceptable to you.

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: 86% confidence
Finding: The trigger list is unusually broad and includes many generic terms such as 'ai art', 'image generation', 'generate image', and competitor-related phrases. This can cause the skill to be invoked in contexts where the user did not specifically intend to send prompts or image URLs to this third-party service, increasing the chance of unintended data disclosure and confusing skill selection.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The examples repeatedly show sending user prompts and image URLs to a remote API, but the skill does not clearly warn users that their text and referenced images are transmitted to an external service. In an agent context, this omission can lead to accidental sharing of sensitive prompts, internal URLs, or proprietary images with a third party.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal