ClawHub
Back to skill

Security audit

Company search wdy

Security checks across malware telemetry and agentic risk

Overview

The skill appears intended for WenDaoYun legal and enterprise lookups, but it needs Review because it may retrieve sensitive personal or legal data under broad triggers without clear handling limits.

Install only if you intend to query WenDaoYun for legal or enterprise records and have authority to handle the returned data. Treat names, phone numbers, case parties, and exit-ban details as sensitive; avoid broad prompts that trigger lookups unintentionally, and redact or minimize results before sharing.

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 description and trigger scope are broad enough to activate on many generic enterprise-information requests without clearly constraining user intent, data categories, or when this tool should be preferred over safer/narrower alternatives. Over-broad triggering can cause unnecessary external data disclosure, unintended handling of sensitive business/legal information, and tool invocation in contexts where the user did not explicitly intend a third-party lookup.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation describes response fields that may include personal data such as phone numbers and named individuals in applicant, respondent, and exit-ban target lists, but it provides no warning about sensitive data handling, minimization, or disclosure risk. In a company-information lookup skill, this omission can cause downstream agents or users to expose or redistribute personal data without adequate caution, increasing privacy and compliance risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.