Security audit

Paragon MLS

Security checks for vulnerabilities and agentic risk

Overview

The skill’s stated real-estate lookup purpose is coherent, but it relies on an unaudited external Node MCP server and non-reproducible setup steps, so users should review it before installing.

Install only if you can inspect and trust the separate paragon-mls-mcp source at the referenced path, pin and verify its dependencies, and accept that some MLS regions may expose or allow tampering with listing queries over HTTP. Prefer a packaged version that bundles the MCP server source, uses package-relative paths, includes a lockfile, and blocks or clearly confirms plaintext HTTP use.

A.I.G

Vulnerability Patterns

Tool Hijacking and SpoofingModifies or replaces tools so legitimate-looking calls execute attacker logic
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T07 · Tool Hijacking and Spoofing

Error

Location: SKILL.md:10
Finding: Core MCP Tool Delegates Execution to an Unbundled External File
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: scripts/build.sh:6
Finding: Unpinned npm Installation Executes an Unverifiable Dependency Supply Chain
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:136
Finding: Paragon API Communication May Use Unencrypted HTTP
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly notes that some Paragon regions return data over HTTP, but it does not give a prominent user-facing warning or require confirmation before transmitting queries. This exposes MLS numbers, listing identifiers, and user search activity to interception or manipulation by network attackers, especially on shared or untrusted networks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.