jf-open-pro-ai-indoor-security

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

Overview

The skill is mostly coherent for indoor security monitoring, but it can change home-security service state and manage biometric member profiles without strong safeguards.

Install only if you trust the publisher and intend to let the agent use your JFTech account token to inspect household security data and change security settings. Keep the credentials scoped and private, and require explicit user confirmation before disabling monitoring or adding, updating, or deleting member face profiles. Also verify the scripts before relying on them operationally, because several helpers reference the move-card signing parameter inconsistently.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence
• Finding: The skill documentation describes use of shell commands and remote API access, but there is no declared permissions model to inform or constrain those capabilities. In a skill that handles device identifiers, JWT tokens, and household monitoring data, undeclared network and shell capability weakens transparency and can enable unintended execution paths or data exposure.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The declared purpose suggests passive indoor security monitoring, but the documented behavior includes administrative actions such as enabling/disabling the service, managing household member face samples, and retrieving historical behavior data from remote APIs. This mismatch can mislead users and reviewers about the true scope of control and surveillance, increasing the risk of unauthorized management actions and privacy-invasive use.

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The trigger phrases are generic household-safety terms that are likely to appear in normal conversation, which raises the chance of accidental invocation. Because this skill can query alerts, manage members, and change service state, unintended activation could expose sensitive household data or alter security settings without clear user intent.

Missing User Warnings

High

• Confidence: 95% confidence
• Finding: The skill performs indoor surveillance-related functions and handles member data, face samples, alerts, and occupancy statistics, yet the description does not prominently warn users about privacy implications. In this context, lack of explicit privacy disclosure is dangerous because users may not understand that the skill can access and manage highly sensitive in-home monitoring data.

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: The script can enable or disable an indoor security monitoring service immediately based only on CLI arguments, with no explicit confirmation step, warning, or safeguard for a high-sensitivity action. In the context of home indoor security, accidental or automated disabling could reduce monitoring coverage and create a real physical-security/privacy exposure window.

Missing User Warnings

Medium

• Confidence: 80% confidence
• Finding: The delete operation removes stored member face profiles immediately once invoked, with no confirmation prompt, dry-run mode, or secondary authorization step. In a biometric member-management context, accidental or unauthorized invocation could delete enrolled identities and disrupt security monitoring or household access workflows.

Static analysis

No suspicious patterns detected.