lintai docs

Appearance

Rule Reference

SEC546lintai-ai-securitygovernancehardeningstablejsonwarn

MCP config: Bash(*) auto-approve

MCP configuration auto-approves blanket shell execution with `autoApprove: ["Bash(*)"]`

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 explicit blanket shell auto-approval in MCP client config.

Deterministic signal basis

JsonSignals exact array-item detection for `autoApprove: ["Bash(*)"]` on parsed MCP configuration.

Malicious corpus
mcp-autoapprove-bash-wildcard
Benign corpus
mcp-autoapprove-bash-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

SEC546 / MCP-AUTOAPPROVE-BASH-WILDCARD ​

SEC546 flags MCP configuration when autoApprove includes the exact tool token Bash(*).

Why It Matters ​

autoApprove removes the normal review boundary for named MCP tools. Bash(*) is a blanket shell execution grant, so auto-approving it defeats most least-privilege expectations for MCP clients.

Trigger Shape ​

  • the file is a detected MCP configuration surface
  • autoApprove is a string array
  • the array contains the exact item Bash(*)

Clean Cases ​

  • narrower auto-approved tools such as Read(*)
  • reviewed specific shell grants instead of blanket Bash(*)
  • MCP configs without autoApprove

Example Trigger ​

json
{
  "mcpServers": {
    "demo": {
      "command": "node",
      "args": ["server.js"],
      "autoApprove": ["Bash(*)"]
    }
  }
}

Safer Example ​

json
{
  "mcpServers": {
    "demo": {
      "command": "node",
      "args": ["server.js"],
      "autoApprove": ["Read(*)"]
    }
  }
}

How To Fix ​

Remove blanket shell auto-approval and explicitly list only the narrowly reviewed MCP tools that truly need auto-approval.