ClawHub
Back to skill

Security audit

Smart Illustrator

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed image-generation skill; its clipboard, temporary-file, external API, and helper-tool behavior are privacy considerations but fit the stated purpose.

Install if you are comfortable with an experimental illustration workflow that can send selected document content or reference images to Gemini/OpenRouter, use local helper tools, write generated files, copy prompts to the clipboard, and leave prompt/config/learning files on disk. Avoid using it on confidential documents unless those data flows and local artifacts are acceptable.

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
95% confidence
Finding
The documentation states that `--prompt-only` will automatically copy generated content to the clipboard without an explicit warning or opt-in. Clipboard contents are globally accessible to the local user session and may be pasted into unrelated apps, so article content or prompts derived from sensitive files could be exposed unintentionally.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
In `--prompt-only` mode, the skill writes a JSON backup containing generated prompt data to `/tmp` and also copies it to the clipboard, but the behavior is not clearly surfaced as a data-handling side effect. `/tmp` is a shared transient location on many systems; while files are usually permission-scoped, storing potentially sensitive prompt material there increases the risk of local disclosure, accidental reuse, or recovery by other processes/users depending on system configuration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.