Security audit

jf-open-pro-device-list

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently queries JFTech device lists, but it can expose device login credentials and tokens in normal output without strong safeguards.

Review before installing. Only use this skill in a trusted workspace, avoid JSON output unless you intentionally need raw device records, and treat any returned passwords or login tokens as credentials that should not be pasted into chats, logs, tickets, or downstream tools.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill documentation describes use of environment variables, file input, and outbound network access, but no explicit permission declaration is present. This creates a transparency and governance gap: users or hosting platforms may not understand that the skill can read local data and contact external APIs, increasing the risk of unexpected data exposure or misuse.

Context-Inappropriate Capability

Medium

Confidence: 98% confidence
Finding: The skill prints device loginToken values in table and simple output even though its stated purpose is device-list querying. Login tokens are sensitive credentials or bearer-like secrets; exposing them in console output, logs, transcripts, or agent responses can enable account/device impersonation and lateral access.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger phrases are broad everyday terms such as '设备列表', '我的设备', and '绑定设备', which can overlap with normal user conversation. Overly generic triggers can cause accidental invocation of a skill that accesses account-bound device data and potentially returns sensitive information, making unintended disclosure more likely in the context of chat or agent orchestration.

Missing User Warnings

High

Confidence: 98% confidence
Finding: The documentation explicitly states that the skill may return sensitive device credentials including username, password, and loginToken, but it does not provide a strong warning, masking guidance, or safe-handling requirements. In this context, accidental exposure of these fields could enable unauthorized access to devices or downstream services, making the issue materially dangerous.

Missing User Warnings

Medium

Confidence: 99% confidence
Finding: Sensitive device login tokens are exposed directly to user-visible output without masking, warning, or access control. In an agent context, this is especially dangerous because outputs may be retained in chat history, system logs, telemetry, screenshots, or copied into downstream tools, causing durable credential leakage.

Static analysis

No suspicious patterns detected.