ClawHub
Back to skill

Security audit

OpenRouter Vision Agent

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal image-analysis skill that sends images and prompts to OpenRouter as part of its stated function.

Install only if you are comfortable sending the selected image URLs, image contents, and prompts to OpenRouter. Avoid using it for private, regulated, or sensitive images unless that provider use is acceptable, and keep the API key in an environment variable rather than writing it into files.

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)

External Transmission

Medium
Category
Data Exfiltration
Content
## Image Analysis

### Via curl

```bash
curl -s https://openrouter.ai/api/v1/chat/completions \
Confidence
93% confidence
Finding
This skill transmits user-provided image URLs and prompts, and potentially sensitive image content, to a third-party external service at openrouter.ai. Although the file explicitly warns about privacy, the skill still creates a real data-exfiltration boundary where confidential images, metadata, or user-supplied API keys could be exposed to an external provider if used improperly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.