ClawHub

跨学科侦探周

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable educational skill for guiding cross-subject study projects, with minor routing and language-scope considerations but no evidence of hidden or unsafe behavior.

Install this if you want a Chinese-language study-planning skill for interdisciplinary projects. Be aware it may activate for fairly general cross-subject or project-learning questions, and it may work with related note or learning-profile skills to organize study history.

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
95% confidence
Finding
The skill description uses very broad trigger phrases such as requests to connect subjects or do project-based learning, combined with language like '必须激活此SKILL' and '务必调用此SKILL.' This can cause unintended over-invocation, crowding out other tools or workflows and giving the skill control in contexts where it may be only partially relevant, which is a prompt-routing security and reliability issue.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill content is written entirely in Chinese and frames activation/output behavior around Chinese-language prompts without any indication of user language preference or opt-in. While not overtly malicious, enforcing a locale can degrade user autonomy, cause confusing responses for non-Chinese users, and increase the chance of misrouting or unusable outputs in multilingual environments.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal