Back to skill

Security audit

Feishu Leave Request

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward helper for submitting Feishu/Lark leave requests and does not include hidden code, persistence, or unrelated data access.

Install only if you intend the agent to help file Feishu/Lark leave requests. Review the leave dates, type, duration, and reason carefully before confirming, because the workflow submits employment-related information to your organization’s Feishu approval system.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description uses broad trigger phrases like wanting to request time off or mentioning taking leave, which can cause the skill to activate on ordinary conversation without a clearly bounded intent. In a skill that drives browser automation and submits HR requests, overbroad activation increases the chance of collecting sensitive personal details or initiating an unintended leave workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to collect leave date, duration, type, and reason, then submit them into Feishu, but it does not explicitly tell the user that these personal and potentially sensitive employment details will be transmitted to a third-party application. This weakens informed consent and can lead to unintentional disclosure of HR-sensitive information through automation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The instructions present bilingual labels and later direct the agent to look for Chinese UI text such as '工作台' and '审批', which assumes a particular Feishu locale. Because no user opt-in or locale selection is offered, this may conflict with language/locale policy expectations for user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.