Back to skill

Security audit

zillow

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently describes Zillow lookups and clearly discloses access through your signed-in browser, with no harmful instructions found.

Install only if you trust the npm server and browser extension to access your Zillow session and saved activity. Pin a reviewed package version, verify the extension download, and prefer project-local configuration when appropriate. The external implementations were not bundled or audited here; the skill also discloses reliance on unofficial Zillow endpoints that may change.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

MCP Config Access

High
Category
Agent Snooping
Confidence
95% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

1. Install zillow-mcp

.mcp.json (project) or ~/.claude/mcp.json (global):

json
{

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
Three of this server's twenty tools take `view: "compact" | "full"` —
**`zillow_search_properties`**, **`zillow_get_by_address`** and
**`zillow_resolve_addresses`** — and on all three **`compact` is the DEFAULT**.
The slim rung is what you get without asking for it.

**Compact here is media stripping, not a field projection.** `src/view.ts`
writes no field list, because this repo holds no captured Zillow payload from