ClawHub
Back to skill

Security audit

jf-open-pro-ai-elderly-care

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its elderly-care purpose, but it handles sensitive monitoring data and can change safety-related settings without enough consent, regional, or confirmation safeguards.

Install only if you are authorized to monitor the device and the monitored person has given appropriate consent or you have lawful caregiver authority. Treat the app secret, authorization token, device serial number, alarm data, routine data, diet data, and any media returned by JSON output as sensitive. Review the hardcoded api-cn.jftechws.com routing before use outside China, and manually confirm any switch or configuration command before running it because the scripts do not provide their own safety prompt.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation instructs users to run local Python scripts and make outbound API calls, which implies shell and network capabilities, but the skill does not declare corresponding permissions. This creates a trust and review gap: consumers or platforms may underestimate what the skill can do, including handling secrets and transmitting sensitive device and monitoring data.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This skill processes highly sensitive elderly-care telemetry, including fall alerts, abnormal behavior, daily routine data, and media URLs for alarm images/videos, yet the documentation does not include an explicit privacy, consent, or data-handling warning. In this context, the omission is more dangerous because the monitored subject may be especially vulnerable, and misuse could expose intimate health and behavioral information without clear authorization boundaries.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script performs a state-changing action that enables or disables an elderly-care monitoring service immediately based on CLI arguments, with no confirmation prompt, dry-run, or explicit warning. In this context, toggling a safety-related monitoring feature for vulnerable users can accidentally disable protections or enable monitoring without deliberate operator acknowledgement, increasing safety and privacy risk.

Static analysis

No suspicious patterns detected.