Vienna

Security checks across malware telemetry and agentic risk

Overview

This is a static Vienna city-guide skill with no code or special access, though some neighborhood guidance is subjective and should be treated cautiously.

Safe to install from a security standpoint. Treat it as a general, static Vienna guide: verify prices, safety claims, immigration or business procedures, and neighborhood recommendations with current official or local sources, and be aware that some wording may reflect subjective or biased assumptions.

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 (4)

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The activation condition triggers on essentially any question about Vienna across tourism, relocation, work, study, or business, without tighter boundaries or disambiguation requirements. Overly broad activation can cause the skill to engage in situations where a more specialized or safety-reviewed skill should handle the request, increasing the chance of irrelevant, stale, or overconfident guidance.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The content uses demographic and nationality-based generalizations such as 'Established Austrians' and frames districts in terms of who belongs there, which can reinforce stereotypes and exclusionary housing narratives. In a relocation/neighborhood recommendation skill, this is more sensitive because users may rely on it for real-world decisions, amplifying biased perceptions about communities.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: Listing 'Language barrier in some shops' as an unqualified con frames multilingual or immigrant-heavy areas as a problem, which can stigmatize communities rather than inform users neutrally. In this skill's context, that wording is somewhat dangerous because it may bias users against diverse neighborhoods under the guise of practical advice.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: The file makes broad, subjective safety characterizations about areas such as 'Immediate area around Praterstern — Sketchy at night' and 'Parts of 10th, 15th, 16th — Less safe feeling' without evidence, scope, or attribution. In a travel-guidance skill, this can mislead users, unfairly stigmatize neighborhoods, and propagate biased or outdated safety claims presented as factual advice.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal