ClawHub
Back to skill

Security audit

Libai Think Partner

Security checks across malware telemetry and agentic risk

Overview

This appears to be a persona-style creative guidance skill with broad prompts, but no evidence of hidden code, credential access, persistence, or data exfiltration.

Install this if you want a broad Li Bai-inspired creative coaching persona. Be aware it may activate for general emotional or motivational prompts, so avoid relying on it for mental health, medical, legal, financial, or other high-stakes advice.

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
87% confidence
Finding
The skill’s activation examples are very broad, covering common creative, emotional, and motivation-related prompts without clear boundaries or opt-in language. This can cause the skill to trigger on ordinary user queries and steer responses into a persona-driven framework the user did not explicitly request, reducing predictability and increasing the chance of inappropriate guidance in sensitive contexts.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The workflow routes generic categories like creativity, pain, aesthetics, and perseverance into fixed response modes without defining trigger thresholds or safety boundaries. In practice, this means ordinary or vulnerable user statements could be interpreted as invitations for persona-based advice, including emotional reframing that may be unsuitable for serious distress or nuanced requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.