ClawHub
Back to skill

Security audit

Tmp.UxeuwjSi9G

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only homes.com MCP helper that clearly discloses its browser-session dependency, though users should understand it can read saved homes and searches from a signed-in account.

Before installing, be comfortable with a browser extension and MCP server using your active homes.com tab to fetch read-only listing data. Avoid asking for saved homes or saved searches unless you intend to expose that account-specific information to the agent session.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger text is overly broad and can cause the skill to activate for general homes.com-related requests, not just clearly intended MCP use. Because this skill can access signed-in browser session data and fetch account-scoped information, over-triggering increases the chance of unintended data access or disclosure during normal conversation flow.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The saved-homes and saved-searches tools operate against the user's authenticated homes.com browser session, but the description does not prominently warn that these actions read account-specific private data. In a skill with natural-language triggers, insufficient disclosure makes accidental invocation and privacy leakage more likely, especially if users do not realize the tool can inspect their signed-in state.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.