ClawHub

Image Editor

Security checks across malware telemetry and agentic risk

Overview

This skill is a local, user-directed image editing helper with no evidence of hidden network use, persistence, credential access, or destructive behavior.

Install only if you want an agent to edit local images using Python/PIL. Review outputs carefully, especially text edits, and expect to adjust the font path or font choice on non-macOS systems.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough to match many generic image-related requests, which can cause the agent to invoke this skill in situations beyond narrow image editing. Over-broad triggering increases the chance of inappropriate tool use, unintended file handling, or bypassing more suitable guarded workflows, especially because the skill includes executable command examples and direct filesystem-style path usage.

Natural-Language Policy Violations

Low
Confidence
76% confidence
Finding
The skill hardcodes a specific font and language context (`STHeiti Light.ttc`, noted as a macOS Chinese font) without requiring user confirmation or checking environment compatibility. This can cause incorrect rendering, missing-font failures, or unintended text appearance changes, which is not severe on its own but can lead to integrity issues in edited content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal