ClawHub

fame graphic

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it generates images through the OpenAI Images API and saves local gallery files, with some privacy and local HTML safety caveats.

Install only if you are comfortable sending illustration prompts and related parameters to OpenAI or to the configured OpenAI-compatible endpoint. Use a scoped API key, verify OPENAI_BASE_URL/OPENAI_API_BASE before running, and avoid opening generated index.html galleries from untrusted prompt content until the HTML escaping issue is fixed.

SkillSpector

By NVIDIA
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
94% confidence
Finding
The skill describes submitting user-provided subjects and prompts to the OpenAI Images API but does not warn that this content leaves the local environment and is sent to an external service. In a creative skill, users may include unpublished story content, proprietary concepts, or sensitive personal material, so the omission creates a real privacy and data-handling risk.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The generated index.html inserts user-controlled values such as subject, prompt, and metadata directly into HTML attributes and element bodies without escaping. If a subject or prompt contains HTML or JavaScript, opening the local report page could execute script in the viewer's browser context, making this a real stored XSS issue in the generated artifact.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal