ClawHub

Company Research Zh

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-oriented company research report skill with no code, install scripts, credential use, persistence, or hidden system access shown.

Safe to install based on the provided artifacts. Treat generated diligence, financial, legal, market, and investment claims as drafts that need independent verification, and request a specific output language if you do not want Chinese.

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
89% confidence
Finding
The skill description contains broad trigger phrases such as company research, due diligence, competitor analysis, and common user search terms, but it does not define clear activation boundaries, exclusions, or required user intent. This can cause the skill to activate unexpectedly for loosely related requests, leading to inappropriate tool use, over-collection of sensitive business information, or accidental generation of authoritative-looking diligence outputs in contexts where the user did not explicitly request them.

Natural-Language Policy Violations

Medium
Confidence
75% confidence
Finding
The skill is primarily written and exemplified in Chinese without clearly stating whether it only supports Chinese interactions or whether multilingual input/output is allowed. This can lead to misrouting, misunderstood requests, or incorrect report generation when users interact in other languages, which is especially risky in due diligence contexts where nuance and factual precision matter.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal