Security audit

anime-calendar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese anime update-calendar helper that uses public web sources and does not request privileged local access or persistence.

Installers should expect Chinese, China-platform-centered results and live web lookups against public anime information sites. Review output against the original platforms for accuracy, since airing times can vary by region and platform.

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

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 (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger description is broad enough to match many ordinary anime-related questions without clear boundaries, which can cause the skill to activate outside its intended scope. This increases the chance of unnecessary web access, incorrect tool use, or the skill overriding more appropriate handlers, especially for generic chat about anime schedules or recommendations.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: L03 的描述全文以中文定义用途和触发方式，且聚焦“国内动漫每周更新日历”，但没有说明这是面向中文用户的区域化技能，也没有为其他语言用户提供选择或退出机制。按规则，未经用户选择而强制单一语言/locale 可能构成自然语言策略问题。

Static analysis

No suspicious patterns detected.