ClawHub
Back to skill

Security audit

te

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Lobster.fun VTuber streaming skill, with normal stream-control risks around credentials and public media playback.

Before installing, verify that the "te" listing is the Lobster.fun skill you meant to use. Store the API key and stream key securely, rotate them if exposed, and moderate chat/media prompts because viewer requests or search terms can affect what appears on stream.

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
90% confidence
Finding
The documentation returns and highlights sensitive credentials (`api_key` and `stream_key`) and instructs users to save and use them, but it does not include any guidance on secure storage, redaction, rotation, or avoiding accidental disclosure in logs, chats, or code snippets. In a streaming/chat-integrated skill, those secrets are especially easy to leak through transcripts, screenshots, client-side code, or prompt output, which could let an attacker control the stream or impersonate the agent.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.