ClawHub
Back to skill

Security audit

cue-cross-border-regulation

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Cue-based legal research connector, but users should avoid sending confidential legal or business details unless they intend to use that external service.

Install only if you are comfortable using Cue as an external research provider. Do not include privileged legal advice requests, personal data, trade secrets, or confidential business plans in the query unless your organization permits sending that information to Cue.

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
88% confidence
Finding
The trigger list contains broad terms such as “GDPR,” “美国法律,” and “foreign law,” which can cause the skill to activate for generic legal or compliance discussions that the user did not intend to route to this external service. Because the skill sends user queries to Cue and downstream sources, overbroad activation increases the risk of unnecessary data disclosure and incorrect tool selection.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Although the architecture section states that requests flow through Cue API to external data sources, it does not clearly warn users before use that their query content will be transmitted off-platform. For a legal-research skill, queries may contain sensitive business plans, compliance concerns, or regulated data, so insufficient disclosure can lead to unintended privacy and confidentiality exposure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.