Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
L004 将“智能日程管理”“时间管理助手”“团队日程协调”等宽泛表述与“常用搜索”并列，未限定具体触发词、使用场景或排除条件。这些短语覆盖大量普通办公请求，容易让系统在非预期上下文中匹配并调用该技能。
- Content
Security audit
Calendar Automation Zh
Security checks for vulnerabilities and agentic risk
Overview
This is a simple calendar helper skill whose calendar and notification access matches its stated purpose, with privacy caveats for shared schedule summaries.
Install only if you are comfortable granting calendar read/write access and notification posting for the calendars and workspaces involved. Before using group briefings or webhook delivery, confirm the destination and avoid sharing confidential meeting titles, attendees, or private schedule details unless intended.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill explicitly supports group schedule briefings and cross-platform calendar syncing, which can expose sensitive event metadata such as meeting titles, attendees, timing, and work patterns to broader audiences or third-party systems. Without privacy warnings, consent checks, or data-minimization guidance, users may unintentionally disclose confidential scheduling information in Slack or during synchronization.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
L002 的名称包含“zh”，且 L003-L004 的主要描述内容均限定为中文，没有说明是否支持其他语言或允许用户选择输出语言。对于通用型日历自动化技能，这种默认强制单一语言的做法可能构成语言策略上的限制。
- Content
Static analysis
No suspicious patterns detected.