ClawHub
Back to skill

Security audit

Resilient ImageGen

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed workflow wrapper for retryable image generation, with confirmation gates for external, paid, or state-changing actions.

Before installing, be aware that this skill can help coordinate image generation through ChatGPT, Computer Use, or API fallback. Use it with project directories you are comfortable writing to, and confirm external uploads or paid API use only when you intend them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The description line mixes English instructions with Chinese promotional text ('Follow/关注作者：微信公众号...') and does not indicate that non-English content is optional or justified by a region-specific purpose. Under the language/locale policy rule, forcing or inserting a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The instruction says 'If exact Chinese text is required,' which embeds a language-specific requirement in the skill description. The file does not provide any user opt-in, alternative locale handling, or justification that this skill is strictly region-specific, so it creates a natural-language locale policy concern.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Route Computer Use and manual ChatGPT branches through `chatgpt-image-handoff`. Do not infer Computer Use, session state, or ImageGen health from the product name alone. Persist the inspected capability state and selection reason.

Treat `cli_api_fallback` as a separate last resort. Use it only after the user confirms the cost and local configuration. Do not ask the user to paste secrets into the conversation.

### 3. Run Built-in ImageGen Safely
Confidence
80% confidence
Finding
Do not ask the user

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.