ClawHub
Back to skill

Security audit

Tmp.2hu3fUVT39

Security checks across malware telemetry and agentic risk

Overview

This Zillow skill is purpose-aligned and disclosed, but users should understand it can use their signed-in Zillow browser session for saved homes and searches.

Install only if you are comfortable letting the MCP use your signed-in Zillow browser session. Use explicit prompts for saved homes or saved searches, and avoid broad Zillow requests if you do not want account-linked activity considered.

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
85% confidence
Finding
The trigger language is broad enough to activate on ordinary Zillow-related conversation, which can cause the skill to run in situations the user did not clearly intend. In this skill, unintended invocation is more sensitive because the tool can access signed-in browser context and retrieve account-linked Zillow data, including saved searches and saved homes.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises access to saved searches and saved homes from a signed-in Zillow session without prominently warning that these are privacy-sensitive, account-specific records. Combined with browser-session routing through fetchproxy, this increases the risk of unintentional disclosure of a user's personal preferences, search activity, and inferred housing interests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.