ClawHub
Back to skill

Security audit

WebChat Image Support

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill enables image understanding as advertised, but users should treat uploaded images as potentially processed by configured vision providers or OpenClaw media services.

Install only if you are comfortable with images sent to the agent being analyzed by your configured vision model or OpenClaw media pipeline. Avoid uploading private screenshots, documents, faces, or regulated data unless the provider and retention settings 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 (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises automatic image handling across channels and explicitly mentions sending images either directly to vision models or to a fallback media-understanding pipeline, but it provides no user-facing disclosure, consent, or data-handling warning. This creates a real privacy and compliance risk because users may upload sensitive screenshots or photos without realizing they will be processed by external models or backend pipelines.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.