Translation Review Skill

• Outcome: Pass
• Latest audit: Jun 10, 2026 at 9:42 AM UTC
• Version:
  0.1.0

Overview

This is a low-risk text guidance skill with slightly broad activation wording but no code, credentials, persistence, or privileged actions.

Safe to install for basic translation-review or language-learning checklists. Be aware it may activate for broader planning requests because its trigger wording is generic; users who want precise behavior should narrow it to source/target translation comparison, terminology, fluency, and fidelity review.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The 'When to use' section is broad enough to match many generic assistance requests, which can cause the skill to activate outside its intended translation-review scope. Over-broad triggering is a real security-relevant weakness because it increases unintended routing and prompt-surface exposure, though this specific skill's content is otherwise low risk and includes sensible safety rules.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The example prompt 'Help me outline a concise plan using the Translation Review approach' is phrased like ordinary everyday speech and could be matched in contexts unrelated to this skill. Such ambiguous trigger text can cause accidental invocation or misclassification, expanding the skill's effective scope beyond its intended domain.

VirusTotal

64/64 vendors flagged this skill as clean.