ClawHub
Back to skill

Security audit

FlashForge AI Flashcard Generator

Security checks across malware telemetry and agentic risk

Overview

This flashcard skill is coherent and stores study cards locally, with no evidence of hidden network, credential, or privileged behavior.

Install only if you are comfortable with generated cards and review progress being stored locally, typically in flashcards.json. Avoid pasting highly sensitive notes unless local retention is acceptable, and manage or delete the deck file when it is no longer needed.

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
76% confidence
Finding
The skill uses broad activation language such as accepting 'any content' and generic 'paste content' workflows without clear trigger constraints or safety boundaries. Overbroad invocation can cause the agent to engage in unintended contexts, including processing sensitive pasted material or performing actions beyond what the user expected from a study aid.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal