ClawHub
Back to skill

Security audit

shift-scheduler

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed shift-scheduling API integration, but users should understand that employee scheduling details are processed by the AI Skills platform.

Install this only if you are comfortable sending staff names, availability, scheduling constraints, and schedule IDs to the AI Skills platform under your account. Avoid unnecessary personal details, review generated schedules before use, and confirm paid operations before generation, update, or export calls.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation encourages users to provide employee availability, dates, and labor constraints, but does not clearly warn that this operational data will be transmitted to an external AI Skills platform API. This creates a transparency and privacy risk: operators may disclose staffing or employee-related data without informed consent, which is especially relevant because the skill explicitly depends on a remote API key and hosted platform.

External Transmission

Medium
Category
Data Exfiltration
Content
- `/api/v1/shift-scheduler/schedule.export`；`/api/v1/shift-scheduler/schedule.export/tasks/{task_id}`

```sh
curl -sS -X POST "$BASE/shift-scheduler/schedule.read" \
  -H "Authorization: Bearer $SHIFT_SCHEDULER_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $REQUEST_UUID" \
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
该文件全部以中文编写，描述了技能的操作方式与结果格式，但没有说明这是面向特定中文用户群体的区域性技能，也没有提供语言选择或 opt-in。根据语言/区域策略，这构成了可能的自然语言政策违规。

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The skill metadata description and the entire markdown content force a single language presentation. There is no indication that the skill is intentionally region-specific or that users can opt into another language, which can violate language or locale policy requirements.

Static analysis

No suspicious patterns detected.