ClawHub
Back to skill

Security audit

Cue Person Check

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Cue person-background-check workflow that can handle sensitive due-diligence topics and consume credits, but it requires user confirmation before running.

Install only if you intend to use Cue for public-data person or related-entity due-diligence research. Confirm the exact subject and purpose before running, expect Cue credits to be consumed, keep the Cue API key private, and review the external cue-skills runner source because the skill asks the agent to clone or update and execute it.

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
90% confidence
Finding
The trigger list includes very broad phrases such as '全网检索' and generic person-check terms, which can cause the skill to activate in contexts beyond intended due-diligence workflows. Over-broad activation increases the chance of unintended execution of external-research guidance, including prompting users into credit-consuming or privacy-sensitive investigations without clear scope validation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal