0d3cb498a3
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
73 lines
2.3 KiB
TypeScript
73 lines
2.3 KiB
TypeScript
import { describe, expect, it } from 'vitest';
|
|
import { getGraderById } from '../../../../src/redteam/graders';
|
|
import { MedicalFdaAiDisclosurePluginGrader } from '../../../../src/redteam/plugins/medical/medicalFdaAiDisclosure';
|
|
import { MedicalFdaCyberAccessControlPluginGrader } from '../../../../src/redteam/plugins/medical/medicalFdaCyberAccessControl';
|
|
import { MedicalFdaCyberAuditTamperingPluginGrader } from '../../../../src/redteam/plugins/medical/medicalFdaCyberAuditTampering';
|
|
|
|
const graderCases = [
|
|
{
|
|
GraderClass: MedicalFdaAiDisclosurePluginGrader,
|
|
id: 'promptfoo:redteam:medical:fda:ai-disclosure',
|
|
expectedText: [
|
|
'intended-use',
|
|
'low confidence',
|
|
'silent model update',
|
|
'data drift',
|
|
'<purpose>',
|
|
'<UserQuery>',
|
|
],
|
|
},
|
|
{
|
|
GraderClass: MedicalFdaCyberAccessControlPluginGrader,
|
|
id: 'promptfoo:redteam:medical:fda:cyber-access-control',
|
|
expectedText: [
|
|
'least-privilege',
|
|
'deny-by-default',
|
|
'replayed packets',
|
|
'factory passwords',
|
|
'<purpose>',
|
|
'<UserQuery>',
|
|
],
|
|
},
|
|
{
|
|
GraderClass: MedicalFdaCyberAuditTamperingPluginGrader,
|
|
id: 'promptfoo:redteam:medical:fda:cyber-audit-tampering',
|
|
expectedText: [
|
|
'SBOM',
|
|
'forensic logs',
|
|
'anomaly alerts',
|
|
'audit evidence',
|
|
'<purpose>',
|
|
'<UserQuery>',
|
|
],
|
|
},
|
|
];
|
|
|
|
describe('FDA medical plugin graders', () => {
|
|
describe.each(graderCases)('$id', ({ GraderClass, id, expectedText }) => {
|
|
it('renders the rubric with standardized tags and plugin-specific criteria', () => {
|
|
const grader = new GraderClass();
|
|
|
|
const rubric = grader.renderRubric({
|
|
purpose: 'medical-device support assistant',
|
|
prompt: 'test prompt',
|
|
});
|
|
|
|
expect(grader.id).toBe(id);
|
|
expect(grader.rubric).toBe('');
|
|
expect(rubric).toContain('medical-device support assistant');
|
|
expect(rubric).toContain('test prompt');
|
|
expect(rubric).toContain('FAIL (score = 0):');
|
|
expect(rubric).toContain('PASS (score = 1):');
|
|
|
|
for (const expected of expectedText) {
|
|
expect(rubric).toContain(expected);
|
|
}
|
|
});
|
|
|
|
it('is registered in the grader registry', () => {
|
|
expect(getGraderById(id)).toBeInstanceOf(GraderClass);
|
|
});
|
|
});
|
|
});
|