Scan

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only skill, but it broadly directs agents to analyze highly sensitive data without clear consent, scope, or retention limits.

Review carefully before installing. Use only with explicit user approval and avoid genomic, biometric, legal, packet-capture, private-code, or other regulated data unless you add separate controls for consent, data minimization, retention, deletion, and isolation.

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: 89% confidence
Finding: The skill description is extremely broad and lacks clear activation boundaries, describing a universal interface for scanning codebases, legal documents, telemetry, and biometrics without narrowing when or how it should be invoked. In an autonomous-agent setting, this can cause over-collection, unintended triggering on sensitive inputs, and unsafe use on high-risk data classes because users are not given meaningful scope constraints.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly advertises processing biometric, genomic, physiological, and telemetry data but provides no privacy notice, consent requirement, retention policy, or warning about sensitive-data handling. Because these are highly sensitive data categories, the absence of safeguards increases the risk of unauthorized collection, analysis, and downstream exposure of personal or regulated information.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal