Jf Open Pro Ai Child Care

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-built for child home monitoring, but it handles sensitive household and child data with weak privacy and credential safeguards.

Install only if you are comfortable connecting this skill to a child-monitoring account and remote JFTech APIs. Use least-privilege, short-lived credentials where possible, avoid passing secrets directly on shared command lines, rotate any exposed app secret, and confirm that household privacy, consent, retention, and legal requirements are handled outside the skill.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (10)

Description-Behavior Mismatch

Medium

Confidence: 87% confidence
Finding: The skill implements active modification of a remote stranger/person database by adding and removing entries, while the stated skill purpose emphasizes passive child-care monitoring and safety awareness. This mismatch expands the skill's authority into identity-management actions that could alter surveillance behavior or records if invoked improperly or through misuse.

Context-Inappropriate Capability

Medium

Confidence: 84% confidence
Finding: The code exposes stranger-library administration capabilities that are not clearly justified by the described child-care monitoring use case. In a home-monitoring context, silent identity-list management can affect who is treated as suspicious and may enable unauthorized operational changes with privacy and safety consequences.

Vague Triggers

Medium

Confidence: 81% confidence
Finding: Broad trigger phrases such as child-care, abnormal alarm, or behavior statistics may overlap with ordinary conversation and unintentionally activate a surveillance-related skill. In a monitoring context, accidental activation can expose private household data or cause sensitive operations to be initiated without clear user intent.

Missing User Warnings

High

Confidence: 93% confidence
Finding: This skill centers on continuous home monitoring and behavioral analysis of children, but the documentation does not warn users about privacy, consent, retention, or surveillance implications. Because the subject matter involves minors and in-home observation, missing privacy disclosures materially increases legal, ethical, and misuse risk.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The document instructs users to configure multiple high-value credentials, including app secrets and authorization tokens, but does not provide guidance on secure storage, rotation, masking, or avoiding accidental disclosure. This increases the chance of credential leakage through shell history, logs, screenshots, or shared environments.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The script requires sensitive values such as appKey, secret, and authorization token to be passed as command-line arguments, which are commonly exposed through shell history, process listings, job control logs, and monitoring tools. In this child-care monitoring context, those credentials can be used to query device alarm data and potentially access sensitive household activity metadata, increasing privacy and account-security risk.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The file contains hardcoded credential-like values for uuid, app_key, and app_secret in the executable test block. Even if intended as demo data, embedding secrets in source code creates a realistic risk of accidental reuse in production, leakage through version control, and normalization of unsafe secret-handling practices. In this child-care monitoring skill context, exposed API credentials could enable unauthorized access to backend services or protected monitoring functions, making the issue more sensitive than in a trivial demo utility.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The script requires secrets and tokens to be supplied as command-line arguments and then sends them to a remote API. Even though the destination is HTTPS, passing credentials via CLI exposes them to shell history, process listings, job control logs, and automation logs, which is a real credential-handling weakness rather than a purely theoretical concern.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The help text advertises a verbose mode that outputs detailed request material, including curl commands and raw responses, but there is no accompanying warning or redaction logic for authorization headers, app secrets, or device/user identifiers. In a child-care monitoring context, this increases the risk of leaking both credentials and sensitive household activity data into consoles, logs, and support transcripts.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The remove operation performs a destructive remote API call without any secondary confirmation, dry-run mode, or safety interlock. In this context, an accidental or unauthorized invocation could delete stranger records and impair downstream monitoring, incident review, or alerting behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal