v1.7.20

pbakaus/impeccablev1.7.20Sep 22, 2026by Ed1s0nZ

Upgrading?

AI Summary

This release integrates CyberStrikeAI with the TypeSafe Jev engine to function as a Human-in-the-Loop (HITL) audit backend. It replaces chat model JSON output with a structured, parallel risk and authorization check mechanism. The system defaults to approving authorized pentesting while blocking destructive operations such as live system destruction, data loss, and configuration changes.

Key Highlights

  • Integration of CyberStrikeAI with TypeSafe Jev for structured HITL auditing.
  • Tool calls are sent to Jev for parallel evaluation of destructive risk and authorization intent.
  • Default policy approves authorized pentesting and blocks live-system destruction, data loss, and config tampering.
  • Custom organization policies can overlay default rules while OpenAI-compatible models remain supported.

New Features

  • CyberStrikeAI and TypeSafe Jev integration
  • Structured pass/block mechanism via System One request
  • Parallel risk assessment logic
  • Default blocking of destructive operations (ACL changes, data loss, etc.)
  • Support for custom organizational policy overlays

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