Back to skill

Security audit

Nintendo Switch Daily Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese Nintendo Switch daily-news reporter that fetches public gaming information and does not request sensitive access or persistence.

Before installing, expect the skill to browse public Nintendo-related sites and produce a Chinese report. The main caveat is that its formatting instructions have small ambiguities, so the system-update section may be handled inconsistently when there is no news.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases include broad everyday wording such as '帮我做 Switch 日报', which can cause accidental invocation in conversations that mention Switch and a daily report without clear intent to run this skill. In an agent environment, overbroad triggering can route user requests to external-fetching behavior unexpectedly, causing unintended browsing, data collection, or incorrect task selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

L108-L111 明确规定“全部中文”,属于语言/locale 约束,但文档未提供用户选择其他语言的选项,也未说明该技能仅面向特定中文区域用户。根据规则,强制单一语言而无用户 opt-in 属于自然语言策略问题。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The format section says the third part should include system updates and explicitly says to note '当日无主机系统更新公告' when there is no update (L072-L074). Later, the notes instruct to '直接省略该部分' if there is no new system update within 36 hours (L134), which directly conflicts with the earlier documented behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.