Security audit

aso

Security checks across malware telemetry and agentic risk

Overview

This skill provides a coherent app-store-listing audit workflow and does not show hidden, destructive, or credential-seeking behavior.

Before installing, expect the skill to access public App Store or Google Play pages, possibly search the web to find an app listing, take listing screenshots if browser tools are available, and read local product-marketing context files if your workspace contains them. Provide exact store URLs when possible to keep the audit scoped.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The trigger description is very broad and includes many common phrasings, which can cause the skill to activate when a user's request only loosely relates to ASO. Unintended invocation matters here because the skill is empowered to fetch live third-party pages and perform web searches, potentially causing unnecessary external access and steering the agent away from the user's actual intent.

Missing User Warnings

Low

Confidence: 87% confidence
Finding: The skill instructs the agent to fetch live listing pages and potentially search the web for an app name, but it does not prominently warn that external third-party requests may occur. This can undermine user expectations and consent, especially when the user shares only an app name and the system expands scope by searching externally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.