v1.7.20
solidtime-io/solidtimev1.7.20Sep 22, 2026by Ed1s0nZ
Upgrading?
AI Summary
CyberStrikeAI has integrated TypeSafe Jev as a Human-in-the-Loop (HITL) audit backend to provide structured pass/block scoring for tool calls, replacing reliance on chat model JSON outputs. This update includes built-in security rules that approve authorized pentesting while rejecting destructive actions, and allows custom organization policies to be layered on top.
Key Highlights
- Supports TypeSafe Jev for structured pass/block scoring
- Built-in rules approve authorized pentesting and reject destructive actions
- Custom organization policies act as overlays
- OpenAI-compatible reviewer remains available
New Features
- CyberStrikeAI integration with TypeSafe Jev
- Parallel risk and authorization intent checking
- Custom approval 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
A free open source IT asset/license management system
A collective list of free APIs
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
Reverse engineer anything with agents, from app behavior down to native binaries.