ClawHub
Back to skill

Security audit

sudocode-gpt-image-2-gen

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed image generation and editing helper that sends prompts and selected images to SudoCode and saves the returned image locally.

Install only if you are comfortable sending prompts and any selected reference images to SudoCode for processing. Prefer SUDOCODE_API_KEY over passing keys on the command line, and avoid confidential or regulated images unless you accept the provider's handling of that data.

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
91% confidence
Finding
The skill instructs the agent to access environment variables for API keys, write generated images to disk, and make outbound network requests to an external service, but it does not declare those capabilities as permissions. This creates a transparency and policy-enforcement gap: operators may approve or run the skill without understanding that it can access secrets, contact third-party infrastructure, and persist files locally.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script sends user-supplied prompts and local image files to a third-party remote endpoint for processing, but it provides no explicit privacy notice, consent prompt, or warning that local files will leave the machine. In a skill context, users may reasonably assume a local transformation workflow, so silent exfiltration of potentially sensitive images or text is a genuine privacy/security issue.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.