Jai Govindani c5ce8cacbf feat(security): add E2E security test harness with LLM judge ... 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		2026-01-29 08:52:59 +07:00
..
auto-response.yml	CI: add auto-response labels	2026-01-27 23:17:22 -06:00
ci.yml	fix: cap windows vitest workers in ci	2026-01-27 15:51:21 +00:00
docker-release.yml	Add Build & Release Docker Image workflows (#1602)	2026-01-24 19:23:55 +00:00
install-smoke.yml	fix: stabilize install smoke against clawdbot installer	2026-01-27 14:58:01 +00:00
labeler.yml	CI: sync labels on PR updates	2026-01-26 19:21:31 -06:00
security-tests.yml	feat(security): add E2E security test harness with LLM judge	2026-01-29 08:52:59 +07:00
workflow-sanity.yml	refactor(test): consolidate temp home + vitest setup	2026-01-09 16:41:05 +01:00