lintai docs

Appearance

Rule Reference

SEC574lintai-ai-securitygovernancehardeningstablejsonwarn

MCP config: Read unsafe path auto-approve

MCP configuration auto-approves `Read(...)` over an unsafe path through `autoApprove`

Public lane
governance
Category
hardening
Provider
lintai-ai-security
Scope
per-file
Surface
json
Tier
stable
Severity
warn
Confidence
high
Detection
structural
Remediation
message only
How to read this lane

Shared authority and workflow policy review.

How to read this category

Least-privilege, provenance, or operational hygiene signal.

Activation Model

Preset Activation

These presets explain where this rule appears in the product experience.

governancesidecar lane
mcpsurface preset

Lifecycle

Stable Lifecycle Contract

State

stable

Graduation rationale

Matches exact unsafe-path `Read(...)` auto-approval in MCP client config.

Deterministic signal basis

JsonSignals exact array-item predicate detection for `autoApprove` entries where `Read(...)` targets an absolute, home-relative, parent-traversing, or drive-qualified path.

Malicious corpus
mcp-autoapprove-unsafe-path-family
Benign corpus
mcp-autoapprove-unsafe-path-family-specific-safe
structured evidence required remediation reviewed
Canonical note

Structural stable rule intended as a high-precision check with deterministic evidence.

Nearby Signals

Related Rules

SEC303MCP config: credential env passthroughMCP configuration passes through credential environment variablesgovernancehardeningjson
SEC394MCP config: wildcard auto-approveMCP configuration auto-approves all tools with `autoApprove: ["*"]`governancehardeningjson
SEC395MCP config: autoApproveTools trueMCP configuration auto-approves all tools with `autoApproveTools: true`governancehardeningjson
SEC396MCP config: trustTools trueMCP configuration fully trusts tools with `trustTools: true`governancehardeningjson
SEC397MCP config: sandbox disabledMCP configuration disables sandboxing with `sandbox: false` or `disableSandbox: true`governancehardeningjson
SEC398MCP config: wildcard capabilitiesMCP configuration grants all capabilities with `capabilities: ["*"]` or `capabilities: "*"`governancehardeningjson

SEC574 / MCP-AUTOAPPROVE-READ-UNSAFE-PATH ​

SEC574 flags MCP configuration when autoApprove includes Read(...) with an absolute, home-relative, parent-traversing, or drive-qualified path.

Why It Matters ​

Read(...) can be useful in narrow scopes, but auto-approving broad unsafe paths removes review from access that extends beyond repository-scoped expectations.

Trigger Shape ​

  • the file is a detected MCP configuration surface
  • autoApprove is a string array
  • an entry matches Read(...)
  • the inner path is absolute, home-relative, parent-traversing, or drive-qualified

How To Fix ​

Replace unsafe Read(...) auto-approval with repository-scoped allowlists or remove it from shared auto-approval.