Security audit

ai-image-gen

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent AI image-generation helper, with expected privacy considerations from sending prompts or reference images to an external API and saving generated files locally.

Before installing, confirm you are comfortable sending prompts and any reference images to the configured Gemini-compatible image API, keep the API key only in environment variables, and choose an output path that is appropriate for the generated content. The artifact does not include the referenced generation script, so verify the actual runtime implementation before relying on it for production or confidential work.

SkillSpector

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 (2)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill documentation indicates it calls an external image-generation API but does not prominently warn users that prompts and reference images will be transmitted off-platform to a third-party service. This can expose sensitive text, proprietary designs, or private images if users assume processing is local or confined to the agent environment.

Missing User Warnings

Low

Confidence: 87% confidence
Finding: The document says generated images are written to disk ('落盘') and later returned, but it does not clearly warn users that local files will be created. This can lead to unintentional storage of sensitive or copyrighted generated content on shared machines, synced folders, or monitored workspaces.

Static analysis

No suspicious patterns detected.