Los Angeles

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only Los Angeles guide with some advice-quality cautions, but no code, credentials, permissions, persistence, or hidden actions.

Safe to install from a security perspective based on the artifacts reviewed. Verify time-sensitive details such as prices, hours, safety conditions, and laws, and be cautious with neighborhood or food-safety advice that could be outdated, overgeneralized, or based on demographic assumptions.

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 (3)

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The activation condition is broad enough to trigger on many generic Los Angeles questions, which can cause the skill to engage outside a clearly bounded purpose. While this is not an exploit by itself, it increases the chance of inappropriate routing, overshadowing more suitable skills, or providing overconfident location-specific guidance when the user's intent is ambiguous.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The guide states that a long line means street food is safe, which is an unreliable health claim and may encourage users to use crowd size as a substitute for actual food-safety indicators. In a travel/practical city guide, readers may act directly on this advice, increasing the risk of foodborne illness if they ignore licensing, temperature control, hygiene, or local health ratings.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The content explicitly segments neighborhood recommendations by protected or identity-adjacent characteristics such as LGBTQ+ status, ethnicity-linked community labels, family status, age cohort, and occupational grouping without any visible user opt-in or sensitivity framing. In a housing or relocation guidance context, this can steer users toward or away from areas based on demographic attributes, creating fair-housing, discrimination, and profiling risk even if the author likely intended to be helpful.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal