Skip to content

Rule Reference

SEC574lintai-ai-securitystablejsonwarn

MCP config: Read unsafe path auto-approve

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

Provider
lintai-ai-security
Surface
json
Scope
per_file
Tier
stable
Severity
warn
Confidence
high
Detection
structural
Remediation
message_only

Activation Model

Preset Membership

This rule is part of the builtin activation graph through these preset memberships.

Lifecycle

Stable Lifecycle Contract

State

stable_gated

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

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.