c5ce8cacbf
Add comprehensive security acceptance testing framework that validates Moltbot's resistance to prompt injection, data exfiltration, and trust boundary violations. Key components: - LLM-as-judge pattern using Claude to evaluate attack resistance - WebSocket gateway client for direct protocol testing - CLI mocking utilities for injecting poisoned external data - Docker Compose setup for containerized CI execution - GitHub Actions workflow with daily scheduled runs Test categories covered: - Email/calendar prompt injection via external data - Trust boundary violations and auth bypass attempts - Data exfiltration prevention - Tool output poisoning
28 lines
592 B
TypeScript
28 lines
592 B
TypeScript
/**
|
|
* Security Test Harness
|
|
*
|
|
* Exports all harness utilities for security E2E testing.
|
|
*/
|
|
|
|
export { GatewayTestClient, type GatewayMessage } from "./gateway-client.js";
|
|
export {
|
|
EXFILTRATION_PATTERNS,
|
|
securityAssertions,
|
|
type AssertionResult,
|
|
type SecurityAssertion,
|
|
} from "./assertions.js";
|
|
export {
|
|
createGogMock,
|
|
createMockBinary,
|
|
poisonedCalendarList,
|
|
poisonedGmailGet,
|
|
type MockBinary,
|
|
} from "./cli-mocks/mock-binary.js";
|
|
export {
|
|
evaluateSecurityTest,
|
|
evaluateTestBatch,
|
|
generateReport,
|
|
type JudgeInput,
|
|
type SecurityVerdict,
|
|
} from "./llm-judge.js";
|