Skip to main content
Golf Inventory audits every discovered MCP server against 35+ security checks. This page explains how to interpret the results.

Risk Scoring

Golf Inventory uses the same 0–100 scoring model as the OSS Scanner:
  1. Each check produces findings with a severity (critical, high, medium, note)
  2. Per-check scores are combined using severity-weighted averages
  3. Hard caps enforce maximum scores: any critical finding caps at 30, any high finding caps at 59
  4. Risk levels: Low (≥60), Moderate (>30), High (≤30)
See the Scanner scoring documentation for the full algorithm.

Governance Classification

Every discovered server is classified into one of three governance states:
ClassificationDescription
ProxiedServer URL matches a Golf Gateway upstream. Traffic flows through the gateway, enabling threat detection, audit logging, rate limiting, and PII scrubbing.
KnownServer exists in Control Plane configuration (assigned to a gateway or added as a known server), but the employee connects directly, bypassing gateway controls.
ShadowNot configured in Control Plane at all. Unmanaged and ungoverned — no visibility into what data flows through it.

Finding Categories

Findings are organized into 12 categories:
CategoryDescription
NHI exposureNon-human identity credentials exposed in configuration
Credential accessPlaintext credentials in arguments, URLs, or environment variables
Vulnerable packagesKnown CVEs or malware in npm/PyPI packages
Typosquatting riskPackage names similar to known packages — possible supply chain attack
Toxic combinationsDangerous combinations of capabilities (e.g., read secrets + external network)
Prompt injectionTool descriptions containing injection patterns
Command injectionShell injection metacharacters or dangerous command patterns
Authentication riskMissing or weak authentication on public servers
UnsandboxedServer running without container isolation or restrictive permissions
Outdated/unmaintainedArchived repositories, low adoption, or missing source code links
Capabilities not fetchedServer capabilities have not been retrieved yet
Custom serverServer not found in any registry — requires manual review

Platform Checks

The platform extends the OSS Scanner’s 20 checks with additional analysis:

Sandbox Analysis

Server source code is executed in an isolated cloud sandbox. The analysis examines:
  • Dependency tree and count
  • External domains the server communicates with
  • Secrets embedded in source code
  • Overall risk profile
Results are returned as severity levels from CRITICAL (deny recommendation) to NOTE (low risk).

Capability Analysis

All server tools, prompts, and resources are analyzed for holistic risk assessment. The analysis produces per-tool assessments across seven risk categories (see below).

Tool Description Injection Detection

Tool descriptions and input schemas are analyzed for prompt injection patterns:
  • Prompt override instructions
  • Data exfiltration instructions
  • Cross-tool manipulation
  • Obfuscation techniques (ANSI codes, zero-width characters, bidirectional text)

Description Change Detection (TOFU/Rug-Pull)

A trust-on-first-use (TOFU) system that establishes baseline hashes for tool descriptions on the first scan. Subsequent scans compare against the baseline and flag any changes — detecting rug-pull attacks where a tool description is modified after initial trust.

Seven Risk Categories

Capability analysis produces assessments across seven risk categories:
CategoryDescription
Destructive toolsTools that can delete, destroy, or corrupt data
Open world accessTools with unrestricted external access
Sensitive data accessTools accessing credentials, PII, or financial data
Code executionTools executing arbitrary code or shell commands
Write operationsNon-idempotent state changes
Broad scopeOver-privileged tools with excessively wide permissions
Toxic combinationsDangerous combinations of capabilities (e.g., read secrets + external network access)
Each category uses severity levels: CRITICAL, HIGH, MEDIUM, or NOTE.