fix(security): gate AI tools by user ability and block admin-URL SSRF

The AI chat assistant scoped tool queries by company but ignored the
per-user Bouncer abilities the rest of the app enforces, so any `use ai`
holder could read customers, invoices, payments, and company financials
their role couldn't otherwise see. Each AiTool now declares a required
ability (entity-aligned); the registry hides unauthorized tools from the
model and refuses to execute them as a backstop.

Separately, admin/owner-supplied URLs were fetched server-side with no
guard against private/reserved targets (SSRF): the AI base URL, the
CurrencyConverter "DEDICATED" exchange-rate URL, and S3/Spaces file-disk
endpoints. A shared PrivateNetworkGuard now backs a PublicHttpUrl
validation rule (save-time) and runtime guards in each driver.

- AiTool::requiredAbility() + mapping across all 12 tools
- AiToolRegistry filters schemas() by ability and re-checks in execute()
- PrivateNetworkGuard / BlockedUrlException / PublicHttpUrl rule (new)
- Rule wired into AI config (service + 3 controllers), exchange-rate,
  and file-disk endpoints; runtime guards in OpenRouterDriver,
  CurrencyConverterDriver, and FileDiskService
- Tests for ability filtering, the guard, the rule, and 422 rejections
This commit is contained in:
Darko Gjorgjijoski
2026-06-05 00:01:09 +02:00
parent 3df2a01832
commit ac2a8ca939
37 changed files with 1052 additions and 74 deletions

View File

@@ -2,6 +2,7 @@
namespace App\Http\Requests;
use App\Rules\PublicHttpUrl;
use Illuminate\Foundation\Http\FormRequest;
class DiskEnvironmentRequest extends FormRequest
@@ -39,6 +40,12 @@ class DiskEnvironmentRequest extends FormRequest
'required',
'string',
],
'credentials.endpoint' => [
'nullable',
'string',
'url',
new PublicHttpUrl,
],
'credentials.root' => [
'required',
'string',
@@ -68,6 +75,8 @@ class DiskEnvironmentRequest extends FormRequest
'credentials.endpoint' => [
'required',
'string',
'url',
new PublicHttpUrl,
],
'credentials.root' => [
'required',