4008 matches found
cupcake
Cupcake Make AI agents follow the rules. Policy enforcement layer for AI agents; yielding better performance and security without consuming model context. Deterministic rule-following for your agents. Interactive Examples Better performance by moving rules out of context and into policy-as-code...
kontext-cli
Website | Documentation | Dashboard | Discord Stop risky AI-agent actions before they run AI agents do more than suggest code. They run shell commands, read files, call services, change infrastructure, and interact with production systems. Kontext puts local policy between AI agents and the tools...
agent-governance-toolkit
🌍 English | Español | 日本語 | 简体中文 | 한국어 Agent Governance Toolkit Ship agents to production without losing sleep 🚀Quick Start · 📋 Specifications · 📦 PyPI · 📝 Changelog -brightgreen !IMPORTANT Public Preview -- production-quality public preview releases. May h...
LID
██╗ ██╗██████╗ ██║ ██║██╔══██╗ ██║ ██║██║ ██║ ██║ ██║██║ ██║ ███████╗██║██████╔╝ ╚══════╝╚═╝╚═════╝ Linux Integrity Drift — "Linux is Dying" — Systematic discovery of kernel code paths that bypass LSM security guarantees The gate was never breached. It was walked around. What is LID? The Linux...
prismor
Prismor Runtime security for Claude Code, Codex, Langchain and other AI agents frameworks/harness. Prismor is highly customizable based on user's own policies. Observe or enforce mode to see agent activity in a local self-serve dashboard Website • Onboard with Skill...
Boucle-framework
Boucle Claude Code hooks that actually enforce your rules. 7 standalone hooks, plus enforce-hooks for CLAUDE.md policy, audit tooling, 1,900+ tests, and a searchable Claude Code gaps corpus with severity ratings and workarounds. Quick links: Check your setup · Install hooks · Known limitations ·...
CVE-2026-93860
In OpenStack Mistral through 23.0.0, the /v2/maintenance API controller clears the request context and calls the maintenance service directly without any policy enforcement. Any holder of a valid Mistral token, regardless of assigned role, can read and change the service's cluster-wide maintenanc...
CVE-2026-93860
OpenStack Mistral versions through 23.0.0 are vulnerable to an authentication bypass issue in the /v2/maintenance API controller. The controller clears the request context and interacts with the maintenance service without enforcing security policies. Consequently, any user with a valid Mistral t...
CVE-2026-93860
In OpenStack Mistral through 23.0.0, the /v2/maintenance API controller clears the request context and calls the maintenance service directly without any policy enforcement. Any holder of a valid Mistral token, regardless of assigned role, can read and change the service's cluster-wide maintenanc...
CVE-2026-50055
A policy-enforcement flaw in Zimbra Collaboration Suite allows an authenticated user to bypass disabled mail forwarding by using a Sieve notify action to send copies of email content and headers to an arbitrary address...
CVE-2026-50055
A policy-enforcement flaw in Zimbra Collaboration Suite allows an authenticated user to bypass disabled mail forwarding restrictions. By using a Sieve notify action to send copies of email content and headers to an arbitrary address, an attacker can exfiltrate emails. This vulnerability was disco...
allstar
Allstar !IMPORTANT OpenSSF가 호스팅하는 Allstar GitHub App은 더 이상 제공되지 않습니다. OpenSSF Scorecard 하위 프로젝트인 Allstar 자체는 계속 유지 관리되며, 이제 직접 실행해야 합니다. GitHub Action으로 실행하거나 서비스 데몬으로 실행할 수 있습니다. 자세한 내용은 ossf/allstar881을 참조하세요. 조직에서 호스팅 앱을 사용 중이었다면 호스팅 앱에서 마이그레이션을 참조하세요. 개요 Allstar란 무엇인가? Allstar의 새로운 기능...
gatekeeper
Gatekeeper Gatekeeper는 OPA와 어떻게 다른가요? OPA와 사이드카 kube-mgmt를 함께 사용하는 방식 일명 Gatekeeper v1.0과 비교하여, Gatekeeper는 다음과 같은 기능을 제공합니다: 확장 가능하고 매개변수화된 정책 라이브러리 정책 라이브러리를 인스턴스화하기 위한 네이티브 Kubernetes CRD 일명 "constraints" 정책 라이브러리를 확장하기 위한 네이티브 Kubernetes CRD 일명 "constraint templates" 뮤테이션 지원을 위한 네이티브 Kubernet...
agentsh
agentsh macOS 참고: ESFEndpoint Security Framework + NENetwork Extension를 통한 네이티브 macOS 적용은 알파 단계입니다. 파일, 프로세스, 네트워크 이벤트가 시스템 확장을 통해 Go 정책 엔진으로 흐르는 종단 간end-to-end 동작은 되지만, 릴리스 사이에 거친 부분과 파격적 변경 사항이 있을 수 있습니다. 현재 프로덕션 용도로는 Linux를 권장합니다. Windows 참고: minifilter 드라이버 서명을 받기 위해 작업 중입니다. 그때까지는 프로덕션 용도로...
opa
Open Policy Agent Open Policy Agent OPA は、スタック全体で統一された、コンテキストを考慮したポリシー適用を可能にする、オープンソースの汎用ポリシーエンジンです。 OPA は、Cloud Native Computing Foundation CNCF ランドスケープにおいて graduated プロジェクトであることを誇りに思っています。詳細については、CNCF の発表をお読みください。 OPA を使い始める Rego Playground で最初の Rego...
Responsible-Alliance-Protocol
目的論的境界プロトコル TBP v4.2.1 自律型AIエージェントのためのポリシー執行および暗号学的監査レイヤー。 TBPは、特定のクラスのエージェント行動 — 自律的な資金移動、産業制御システムへのアクセス、兵器システムとの統合 — を、モデル自身の推論の外側にある実行レイヤーでブロックする。決定は署名され（HSMバックド）、タイムスタンプが付与され（RFC...
agent
Bomfather Agent Bomfather Agentは、カーネル空間で動作し、ポリシーに基づいてアクションをブロックするeBPFベースのエージェントです。 私たちは、既存のソリューションで抱えていた問題を解決するためにこのエージェントを開発しました。 1. セットアップと使用が複雑すぎた。 2. 遅く、非効率だった。 3. そして、たとえセットアップが簡単であっても、セキュリティが不十分であったり、さまざまなユースケースに対応できるだけの柔軟性がなかった。 これらの点は、このプロジェクト全体を通じた私たちの北極星です。すべての機能と開発は、これらの点を満たすことを目的としていま...
Protection Mechanism Failure
Overview Magick.NET-Q16-HDRI-AnyCPU is a Magick.NET allows you can use ImageMagick without having to install ImageMagick on your server or desktop. More information about specific builds see the official docs https://github.com/dlemstra/Magick.NET/tree/main/docs Affected versions of this package...
aegisagent
AegisAgent — AI Agent Runtime Security Gateway AI Agent 运行时安全网关——密码学绑定每次工具调用到真实模型补全，零信任策略执行，沙箱隔离与人工审批一体化。 背景：为什么需要 AegisAgent 2026 年 8 月，Cloud Security Alliance 披露了 CoreBreak 漏洞族 ，这一系列严重漏洞彻底打破了 AI Agent 生态的安全假设： CVE 编号| 影响组件| 风险描述 ---|---|--- CVE-2026-18830| LLM 工具调用链| 模型补全结果可被中间人篡改，工具调用与 LLM...