Jf Open Pro Ai Outdoor

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-built for outdoor camera security, but it can change monitoring settings and handles sensitive credentials in ways users should review before installing.

Install only if you trust the publisher and intend to let the agent control JF outdoor-security settings. Before use, remove or rotate any embedded credential-like values, avoid passing secrets directly on command lines, and require explicit user confirmation before service toggles, deletes, credential sync, or configuration changes.

SkillSpector

By NVIDIA

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Context-Inappropriate Capability

Medium

Confidence: 96% confidence
Finding: The file contains embedded credential-like values and code to generate API authentication signatures, which directly enables authenticated interaction with an external platform if those values are real or reused. In a security-camera/outdoor monitoring skill, signing requests is functionally relevant, but hard-coding example secrets in executable code creates a credential exposure and misuse risk rather than just documentation noise.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger phrases are broad capability terms like '异常告警', '智能检测', and '车辆管理' without clear scope restrictions or exclusion conditions. In an agent setting, this can cause accidental invocation in loosely related conversations, leading to unintended API calls that read or modify device and account state.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The document describes operations that can change device configuration, enable or disable services, save push plans, alter detection areas, and delete vehicle records, but it does not prominently warn about operational impact or irreversible effects. Users may invoke these actions without understanding they can disrupt monitoring, notifications, or stored data.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: The script accepts highly sensitive values such as the app secret, authorization token, device username, and device password via command-line arguments. On many systems, command-line arguments are exposed through process listings, shell history, audit logs, or job control systems, which can leak credentials to other local users or operators.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: Hard-coded credential-like values in an executable __main__ test block are a real secret-management flaw because they are easy to commit, leak, and accidentally execute. If exposed through source control, logs, packages, or copied examples, an attacker could generate valid request signatures and access or abuse the associated API.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal