Add Flashcard

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only flashcard skill with no bundled executable code, installs, credential use, or hidden high-impact behavior.

Reasonable to install if you want an agent shortcut for adding flashcards. Be aware it relies on a separate local capability_executor.py not included here, so review that local implementation before trusting what it stores or reports, and consider narrowing triggers if accidental activation would be annoying.

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 trigger list includes broad everyday phrases such as "flashcard," "review," and "create card" equivalents without clear contextual constraints, which can cause the capability to activate when the user did not intend to invoke this skill. In an agent environment, overly permissive trigger matching can misroute user requests, causing unintended tool execution and increasing the chance of confusing or unsafe automation behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal