Study Buddy

• Outcome: Review
• Latest audit: May 29, 2026 at 9:26 PM UTC
• Version:
  1.2.0

Overview

Study Buddy is a coherent flashcard tool, but its local deck file operations need review because deck names are only partially constrained before creating, importing, exporting, and deleting files.

Review before installing. Use it only for study material you are comfortable storing locally, avoid sensitive notes unless local retention is acceptable, and avoid unusual deck names or untrusted imported deck JSON until filename validation and delete confirmation are improved.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill invokes a Python script that creates, updates, exports, imports, and deletes deck files, which is a file-write capability, yet no corresponding permission or user-facing disclosure is declared. Hidden write access increases risk because a user may invoke a seemingly harmless study feature without realizing it persists or modifies local data in the home directory.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 93% confidence
• Finding: The declared description frames the skill as a study assistant, but the documented behavior also includes arbitrary local file import, persistent local storage, export of full deck contents, and destructive deletion. This mismatch is dangerous because it can lead users or orchestrators to authorize the skill under a narrower trust model than its actual data-handling and filesystem capabilities warrant.

Vague Triggers

Medium

• Confidence: 78% confidence
• Finding: The trigger phrases are broad enough that normal conversation about studying, reviewing, or memorizing could invoke the skill unexpectedly. Unintended invocation matters here because the skill can persist data and manipulate local deck files, so accidental activation could cause unwanted storage or state changes.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill stores decks, review history, and scheduling metadata under the user's home directory but does not clearly warn users about retention. Persistent study materials may contain sensitive notes or copyrighted/private content, so undisclosed storage creates privacy and data-governance risk.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The documented delete command removes deck files from disk without any warning about permanence or confirmation step. In a conversational interface, destructive commands are especially risky because ambiguity or accidental invocation can lead to irreversible loss of study materials and history.

VirusTotal

64/64 vendors flagged this skill as clean.