ClawHub

rant-translator

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only rant and sarcasm translation helper with no executable code or hidden data access, though its broad trigger and sarcastic defaults can produce socially risky wording.

Install this only if you want a humor-oriented sarcasm translation helper. Review outputs before posting, avoid private names or workplace details when possible, and treat the risk score as informal advice rather than a reliable platform-safety guarantee.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
90% confidence
Finding
The trigger logic is very broad and activates on common complaint, sarcasm, or mixed-language phrasing, which can cause the skill to engage outside the user's actual intent. In context, that can unexpectedly transform ordinary conversation into insulting or culturally stylized content, increasing the chance of harmful outputs, moderation issues, or user confusion.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The skill defaults to producing specific locale-styled sarcastic outputs and says to provide culture-adapted variants by default, even when the user may not have requested them. In this skill's context, that is more dangerous because it is explicitly designed to generate passive-aggressive or mocking language, so unrequested style changes can escalate harassment, cause cross-cultural offense, or create policy-violating content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal