Security audit

Gaming Session Scheduler

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only gaming time-planning skill with no evidence of hidden network access, persistence, credential use, or destructive behavior.

This skill appears safe to install if you want text guidance for planning gaming sessions around real-life duties. Expect it to provide structured advice rather than integrate with calendars, games, parental controls, or screen-time systems.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared description promises a domain-specific coaching skill for managing gaming time and responsibilities. The supplied code instead implements a generic markdown-backed skill handler that loads SKILL.md, extracts metadata and sections, and formats them into a response. Its primary purpose is template/metadata rendering, not providing gaming-life balance advice or enforcing play-window/stop-rule logic. While it does not perform dangerous external actions, the actual behavior is materially different from the declared purpose.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared purpose describes an end-user coaching skill focused on balanced gaming habits. The actual code does not implement gaming guidance, planning, launch conditions, stop rules, or balance recommendations. Instead, it tests infrastructure functions for loading skill metadata/templates and returning descriptive cards or raw prompt/meta content. This is a materially different primary purpose, so the description does not accurately represent the supplied code chunk.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest says this skill should help users fit gaming into real life with safe play windows, launch conditions, stop rules, and balance guidance. Instead, the handler reads SKILL.md and formats its sections into a generic guidance card, without implementing any scheduling, balance assessment, or decision logic specific to gaming sessions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The markdown includes a natural-language localization choice by presenting a Chinese name, but it does not indicate whether language is optional or user-selected. Under the policy rule for language/locale, fixed locale presentation without opt-in can be a minor policy issue when no choice or justification is provided.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The generated status line says the handler 'returns a descriptive guidance card and does not perform external actions.' However, the same handler also supports 'meta' and 'prompt'/'template' modes that return raw skill metadata and the full SKILL.md body, which is broader behavior than the status text describes. While not a dangerous contradiction, the documentation-like output understates what the code actually exposes.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.