ClawHub
Back to skill

Security audit

AI翻译验证(免费版)

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed translation workflow that uses an external API as part of its stated purpose, with no hidden persistence or destructive behavior found.

Install only if you are comfortable sending selected text or documents to the external translation API and using a TRANSLATE_API_KEY in requests. Review curl/Python commands before running them, avoid sensitive or regulated documents unless you have appropriate approval, and choose output filenames carefully to prevent overwriting existing files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
The skill declares the `exec` tool even though its stated purpose is translation. Granting general-purpose command execution expands the attack surface substantially, because a prompt-triggered workflow could run arbitrary shell commands beyond translation tasks, especially in an agent environment that may have filesystem and network access.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger condition is broad enough that common requests about translation, localization, or multilingual handling could invoke the skill unintentionally. In an agent setting, this increases the chance of accidental API calls, file handling, or data transmission without the user clearly intending to use this external service.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill does not prominently warn that provided text and uploaded files are sent to an external translation API. This is dangerous because users may unknowingly disclose sensitive documents, personal data, or proprietary content to a third party, creating confidentiality and compliance risks.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The automated download flow writes output files locally without clear warning about overwrite behavior, output paths, or the trustworthiness of generated artifacts. In practice, this can overwrite existing files or place unexpected content on disk, which is especially risky in automated agent workflows.

External Transmission

Medium
Category
Data Exfiltration
Content
-F "title=auto_$FILE" | jq -r '.data.project_id')
# ...
# 确认项目
curl -s -X POST https://api-verify.example.com/project/confirm \
  -H "Authorization: Bearer $API_KEY" \
  -d "project_id=$PROJECT"
# ...
Confidence
90% confidence
Finding
curl -s -X POST https://api-verify.example.com/project/confirm \ -H "Authorization: Bearer $API_KEY" \ -d

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.