ClawHub
Back to skill

Security audit

Pilot Translate

Security checks across malware telemetry and agentic risk

Overview

This translation skill is coherent, but users should review it because it normalizes sending agent message contents, including a customer-data example, through third-party translators without privacy warnings.

Review before installing. Use only verified translation tools, avoid the shortened sudo install snippet unless you independently trust the source, and do not translate secrets, credentials, customer records, personal data, or regulated content unless your organization has approved that translation backend. Prefer self-hosted or enterprise-approved translation for sensitive messages, confirm Pilot recipients, and disable auto-translation when it is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs users to send message content through external translation tools and services, including Google Translate and DeepL-style workflows, without any warning that message contents may leave the local environment and be exposed to third-party systems. In the context of agent-to-agent communication, messages may contain sensitive operational data, customer information, or internal prompts, so this creates a real confidentiality and compliance risk rather than a purely theoretical concern.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.