jf-open-pro-ai-joblover

• Outcome: Review
• Latest audit: Jul 30, 2026 · 1:47 PM UTC
• Version: 1.0.1

Overview

The skill is coherent for JF Tech employee duty monitoring, but it handles surveillance data, credentials, and monitoring configuration changes without enough safeguards or warnings.

Install only in an environment authorized for employee monitoring, with a clear legal basis and access controls. Avoid verbose mode unless you can protect terminal output, logs, and screenshots, and treat app secrets and authorization tokens as sensitive. Use extra caution before allowing an agent to disable monitoring or delete duty plans.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill documents shell and network-capable operations but does not declare corresponding permissions or clearly scope those capabilities. This creates a transparency and governance gap: users or hosting systems may underestimate what the skill can do, increasing the risk of unintended command execution or external data transmission once the referenced scripts are used.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 86% confidence
• Finding: The stated description emphasizes real-time monitoring and notifications, but the documented behavior includes administrative actions such as enabling/disabling service and adding/removing duty plans. This mismatch can mislead operators about the skill's actual control surface, causing them to grant trust or run it in contexts where configuration changes to surveillance systems are not expected.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill is centered on employee monitoring, abnormal-behavior detection, and behavioral statistics collection, yet it lacks a clear privacy, consent, retention, and lawful-use warning. In this context, the omission is significant because the skill facilitates surveillance of workers and access to sensitive behavioral records, which can create legal, compliance, and abuse risks even if the underlying API is legitimate.

Missing User Warnings

Low

• Confidence: 81% confidence
• Finding: The documentation presents service enable/disable and plan deletion operations as routine actions without warning about their operational consequences. In a monitoring/safety context, disabling inspection or deleting plans could silently reduce oversight, interrupt alerts, or create gaps in evidence and compliance coverage.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: Verbose mode prints a full curl command containing sensitive values including Authorization, appKey, uuid, and a request signature derived from secrets. This can leak credentials into terminal scrollback, logs, screenshots, CI output, or chat transcripts, enabling unauthorized API access or replay within token validity windows.

External Transmission

Medium

• Category: Data Exfiltration

Content

重要：
    - 所有查询直接使用 API，不使用缓存
    - 输出包含完整 curl 命令和原始响应
    - 以实际 API 响应为准，不编造解释
"""

• Confidence: 92% confidence
• Finding: The script is explicitly designed to transmit device identifiers and authentication material to an external vendor API, and its documentation emphasizes direct API access plus raw response output. In this skill context, external transmission is expected, but it becomes security-relevant because highly sensitive operational data and credentials are handled without minimization, redaction, or clear safeguards.

Static analysis

No suspicious patterns detected.