Security audit

Tmp.Vhc8CftFa4

Security checks across malware telemetry and agentic risk

Overview

This Redfin helper is read-only and purpose-aligned, but it can surface saved Redfin account data through the user's signed-in browser session.

Install only if you are comfortable letting the MCP use your active Redfin browser session to read saved homes and saved searches. Public listing tools are read-only, but account-linked saved activity may appear in agent responses when you ask for it or invoke related Redfin saved-data requests.

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: 89% confidence
Finding: The trigger text is broad enough to activate on many generic Redfin-related requests, including requests that may implicitly involve a user's signed-in account state. In this skill, that matters because the toolset includes access to saved homes and saved searches through the user's authenticated browser session, increasing the chance of unintended invocation and privacy-impacting data access.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly supports retrieval of saved homes and saved searches from a signed-in Redfin session, but the description does not prominently warn that personal account data may be accessed. Without a clear privacy notice, users may not realize that invoking the skill can expose account-specific data from their browser session, leading to unintended disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.