ClawHub
Back to skill

Security audit

USA零生图技能

Security checks across malware telemetry and agentic risk

Overview

This skill sends user-provided image prompts and reference images to the stated image API and saves generated image files locally, with the main risks disclosed to the user.

Before installing, only use this with a dedicated, revocable usa0.top image-generation API key and avoid sensitive prompts or images. Do not use --base-url unless you explicitly trust the destination, because the API key and request content will be sent there.

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 clearly performs sensitive actions including reading environment variables, writing files, and making network requests, yet it does not declare permissions. This creates a transparency and consent problem: a host or user may not realize the skill can access secrets like USA_API_KEY, fetch remote content, or write generated artifacts locally. The context increases concern because the skill explicitly handles API keys and can send them to a configurable base URL.

External Transmission

Medium
Category
Data Exfiltration
Content
response = requests.post(url, data=form_fields, files=files, headers=headers, timeout=(30, 300))
        else:
            url = f"{args.base_url}/v1/images/generations"
            response = requests.post(url, json=common_fields, headers=headers, timeout=(30, 300))
        response.raise_for_status()
    except ImageGenerationError:
        raise
Confidence
91% confidence
Finding
requests.post(url, json=

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
README.md:11

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:117