ClawHub
Back to skill

Security audit

ImageCraft Editor

Security checks across malware telemetry and agentic risk

Overview

This is a coherent StepFun image-editing app template, but it needs review because it sends and stores user photos without strong disclosure, retention controls, or endpoint restrictions.

Review before installing or using with real users. Only use it if you are comfortable sending uploaded images to StepFun, restrict STEPFUN_BASE_URL to approved StepFun HTTPS endpoints, keep the API key server-side, and add visible consent plus deletion or retention controls for uploaded and generated images.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tainted flow: 'STEPFUN_EDIT_URL' from os.getenv (line 25, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Content
}

    try:
        resp = requests.post(STEPFUN_EDIT_URL, json=payload, headers=headers, timeout=120)
        resp.raise_for_status()
        data = resp.json()
Confidence
95% confidence
Finding
resp = requests.post(STEPFUN_EDIT_URL, json=payload, headers=headers, timeout=120)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill instructs users to build a project that uses environment secrets and outbound network access, but it does not declare those capabilities as permissions. This creates a transparency and governance problem: users or orchestration systems cannot accurately assess that the skill will handle API keys and send image data to an external service.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The endpoint sends user-uploaded images to a third-party API, but the backend code shows no mechanism for user disclosure, consent, or privacy notice. For an image editing app, uploads may contain faces, IDs, or other sensitive content, so silent external transmission creates a real privacy and compliance risk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.