Accessibility

Security checks across malware telemetry and agentic risk

Overview

This is a coherent accessibility guidance and read-only auditing skill with no evidence of hidden execution, data exfiltration, persistence, or destructive behavior.

Install this if you are comfortable with an accessibility auditor reading and searching relevant project source files when asked to audit UI code. Avoid running broad audits in directories containing unrelated sensitive material, and prefer pointing it at the specific page, component, or source folder you want reviewed.

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 (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The manifest description says the agent 'MUST BE USED' and 'Use PROACTIVELY' for a broad set of common accessibility tasks, which can cause over-triggering beyond clearly bounded audit scenarios. In an agentic system, overly broad activation increases the chance this skill is invoked on many unrelated requests, expanding tool use and analysis scope in ways the user did not explicitly request.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal