ClawHub
Back to skill

Security audit

Global Health Public Health Data

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed public-health data lookup skill that uses an AgentPMT remote tool and does not include local executable code or hidden persistence.

Install this if you want AgentPMT-backed global health data lookups. Be aware that queries are remote, may cost 10 credits each, and should be used only for public-health or World Bank-style data requests rather than generic country questions.

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 (1)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The skill advertises broad activation keywords such as generic phrases around querying health data, country, or region, which can cause over-selection in unrelated contexts and trigger external tool calls when a simpler or local answer would suffice. In an agent ecosystem, this increases the chance of unnecessary remote data transmission, paid invocations, and unintended workflow routing.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal