Personal Statement

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward healthcare admissions personal-statement helper with no evidence of hidden access, exfiltration, persistence, or destructive behavior.

Use this for healthcare admissions essays, but keep inputs minimal: de-identify patient stories and avoid unnecessary names, dates, medical details, or other sensitive personal information. Review outputs for accuracy and authenticity, and note that some documented Python examples refer to helper APIs not included in the package.

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: 88% confidence
Finding: The skill’s invocation guidance expands beyond a narrowly scoped personal-statement tool into generic academic-writing tasks, which can cause the agent to select this skill for requests it was not designed to handle. That scope drift increases the chance of inappropriate reuse, unsupported assumptions, or generation of application materials outside the validated workflow, weakening safety and reliability boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal