v1.7.20
vercel/satoriv1.7.20Sep 22, 2026by Ed1s0nZ
Upgrading?
AI Summary
Integrates TypeSafe Jev as a Human-in-the-Loop (HITL) audit backend to handle tool call approvals structurally. The system now evaluates risks like data destruction or config tampering via local rules while allowing authorized penetration testing, with custom policies stacking on top of default settings.
Key Highlights
- Support for TypeSafe Jev as a structured audit engine for non-allowlisted tool calls.
- Built-in rules prioritize authorized activity and block destructive operations (data loss, live config changes).
- Custom organization policies are evaluated as overlays on top of default rules.
- Maintains OpenAI-compatible protocol for reviewer selection.
New Features
- TypeSafe Jev HITL integration
- Structured pass/block scoring for tool calls
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
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.
The open source coding agent.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.