ClawHub

Tibetan Translation

Security checks across malware telemetry and agentic risk

Overview

This is a translation reference guide with no code execution, credential use, persistence, or hidden system access.

Safe to install as a translation aid. Review outputs for accuracy, register, cultural sensitivity, and religious terminology, especially for formal or Buddhist texts, and specify modern, mixed-script, transliteration, or Western punctuation preferences when needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrase "any content" is overly broad and can cause this specialized skill to activate for nearly all English↔Tibetan translation requests, including cases where a more general translation or policy-aware skill should take precedence. This increases prompt-selection ambiguity and can lead to inappropriate application of domain-specific defaults such as religious terminology, register assumptions, or formatting conventions.

Natural-Language Policy Violations

Low
Confidence
76% confidence
Finding
The skill presents Tibetan punctuation conventions as the default and uses strong prescriptive language, which can override user expectations in mixed-script, modern, educational, or transliteration contexts. While not a security exploit in the traditional sense, it can cause undesired output formatting and reduce reliability by imposing locale-specific conventions without checking user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal