ClawHub
Back to skill

Security audit

Translate TXT

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it translates selected text files through an external AI API, with privacy and API-key handling risks users should understand.

Install only if you are comfortable sending the selected text files to the configured translation provider. Avoid using it for confidential, regulated, or proprietary documents unless that provider is approved for that data, and protect or remove the skill-local .env file if it stores your API key.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are broader than the documented .txt-only purpose, especially phrases like '翻译文本' and 'translate file', which can match generic translation requests for arbitrary content. This can cause the skill to activate unexpectedly and route sensitive or unsupported files through a workflow that uploads content to an external API.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script transmits user-supplied file contents, glossary extracts, and inferred background context to a remote LLM/translation API, but it does not present an explicit warning or confirmation at runtime. This can lead to unintentional disclosure of sensitive or regulated data if users assume translation happens locally.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script stores the API key in a local .env file during non-interactive setup without any warning, permission hardening, or guidance about the sensitivity of that file. This can lead to credential exposure via accidental commits, broad file permissions, backups, or other local users/processes reading the file.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.