v1.7.20

LaurenzV/hayrov1.7.20Sep 22, 2026by Ed1s0nZ

Upgrading?

AI Summary

Integrates TypeSafe Jev as a Human-in-the-Loop (HITL) audit backend for CyberStrikeAI, replacing chat JSON outputs with structured pass/block scores for tool calls.

Key Highlights

  • Structural pass/block scoring via Jev instead of chat model JSON output.
  • Parallel evaluation of destructive risk and authorization penetration intent.
  • Default policies block live system destruction, data loss, and ACL changes.
  • Custom organizational policies overlay on default rules.

New Features

  • TypeSafe Jev integration for HITL audit
  • Structured tool call approval scoring
  • Local rule-based approval/rejection logic
  • Custom organizational policy overlay support

Full Release Notes

CyberStrikeAI 现已接入 TypeSafe Jev 作为人机协同审批引擎:Agent 每次非白名单工具调用,会把工具名、参数和策略一次性交给 Jev 做结构化放通/拦截,不再依赖聊天模型输出 JSON。Jev 并行判断破坏性风险与授权渗透意图,本地规则合成 approve/reject;默认放行授权渗透,只拦截打挂业务、毁数据、改账号权限或改线上配置的操作。自定义审批策略会作为组织规则叠加,OpenAI 协议小模型仍可选用。

---

CyberStrikeAI now supports TypeSafe Jev as a HITL audit backend. Each non-allowlisted tool call is sent to Jev in one System One request, which returns structured pass/block scores instead of chat JSON. Built-in rules approve authorized pentest activity and reject live-system destruction, irreversible data loss, account/ACL changes, and config tampering. Custom org policy is evaluated as an overlay; the OpenAI-compatible reviewer remains available.

Related Repositories