ClawHub
Back to skill

Security audit

Hot Analyzer

Security checks across malware telemetry and agentic risk

Overview

This skill fetches public Chinese hot-list data and creates local analysis files, with no evidence of credential access, persistence, destructive actions, or hidden data handling.

Install only if you are comfortable with the agent contacting Toutiao, Baidu, Weibo, Douyin, and Zhihu hot-list endpoints and saving fetched public trend data plus generated reports in the current workspace. Treat the financial-market conclusions as analysis, not trading advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger phrases are very broad and can activate on ordinary discussion of current events or generic analysis requests. Over-broad activation increases the chance of unexpected network access, file creation, and external processing without clear user intent to invoke this skill.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill directs collection from five external APIs in parallel but does not provide a user-facing warning or consent step for network data access. In an agent environment, silent external requests can leak usage patterns, surprise users, and violate least-privilege expectations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.