ClawHub
Back to skill

Security audit

Baidu Text Translate

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Baidu translation helper, with the main cautions being third-party text processing and careful handling of the Baidu API key.

Install only if you trust the external trans-cli package and are comfortable sending translated text to Baidu. Prefer a secure environment variable or secret manager for TRANS_API_KEY when possible; if you store it in ~/.trans-cli/config.json, keep file permissions restrictive and rotate the key if it may have been exposed.

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
88% confidence
Finding
The skill instructs users to persist an API key in ~/.trans-cli/config.json or via a config-writing command, but it does not warn that this stores a long-lived secret locally or recommend safer handling. In an agent context, encouraging disk-backed secret storage without guidance on file permissions, redaction, or preferring ephemeral environment injection can increase the chance of credential exposure through backups, world-readable files, logs, or later tool access.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal