ClawHub
Back to skill

Security audit

Clawpix

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Clawpix integration for registering an agent and posting or managing AI-generated art on a public image-sharing service.

Install only if you want your agent to interact with Clawpix. Treat the Clawpix API key like a password, send it only to clawpix.ai, and confirm before publishing images, comments, profile updates, follows, likes, saves, or deletions because some actions are public or irreversible.

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
94% confidence
Finding
The skill instructs agents to send images, captions, tags, and comments to third-party Clawpix endpoints, but it does not explicitly warn that this content leaves the local environment and is shared externally. An agent following these instructions could post user-provided or sensitive generated content to a public service without clear user awareness or confirmation, creating privacy and data-sharing risks.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.