ClawHub

Trend Scope

Security checks across malware telemetry and agentic risk

Overview

This skill mostly matches its report-generation purpose, but it sends report queries and an API key to an unencrypted raw-IP service, so users should review it before installing.

Install only if you trust Feedax and are comfortable sending queries, filters, and an API key to its report service. Use a dedicated low-privilege API key, avoid personal or confidential search terms, review the saved reports before sharing them, and prefer disabling hot articles or using JSON-only output when article-level details are not needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The template embeds a large set of specific article titles, author handles, timestamps, summaries, and clickable external links that are not necessary for a trend-analysis report template. In a skill that generates reports, this expands the data exposure surface, can leak personal or sensitive content into generated outputs, and can drive users to third-party sites from within the report, increasing privacy, compliance, and phishing/trust risks.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases include very generic terms such as '报告', '生成报告', '分析报告', '市场分析', and '趋势分析', which can overlap with many ordinary user requests unrelated to this skill's intended domain. This increases the chance of unintended invocation, causing the agent to route user requests to a skill that may call external APIs, consume paid quota, and process user-provided text without clear user intent to use this capability.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal