ClawHub
Back to skill

Security audit

Openai Image Gen 1.0.1

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it sends image prompts to the OpenAI Images API and saves generated images plus a local gallery.

Install only if you are comfortable sending prompts to the configured OpenAI API endpoint and storing generated prompts locally. Use a dedicated API key, check OPENAI_BASE_URL/OPENAI_API_BASE if set, and avoid putting sensitive or untrusted HTML-like text in prompts before opening the generated gallery.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill requires access to an API key in the environment and makes outbound network requests, but the manifest does not declare those capabilities. This creates a transparency and consent problem: users or orchestration systems may run the skill without understanding it can exfiltrate prompt data to a third-party service and consume a sensitive credential.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The run instructions tell users to execute a script that sends prompts to the OpenAI Images API and writes image files, JSON metadata, and an HTML gallery locally, but the skill description does not warn about either behavior. This omission can lead to unintended disclosure of prompt content to an external service, unexpected API usage/costs, and unanticipated persistence of generated content on disk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.