Lucene search
+L

60 matches found

Kitploit
Kitploit
added 2026/08/27 1:38 a.m.3 views

secure-agent-playbook

सुरक्षित एजेंट प्लेबुक AI एजेंटों के लिए एक ओपन-सोर्स सुरक्षा प्लेबुक। संरचित, OWASP-आधारित प्रक्रियाएं जो एजेंटों को कोड समीक्षा से लेकर AI एजेंट सुरक्षा ऑडिट तक सुरक्षा इंजीनियरिंग कार्य करने में सक्षम बनाती हैं। विषय सूची यह क्यों उपयोग करें? यह क्या है? त्वरित प्रारंभ कौशल सूची एजेंट उदाहरण...

5.4AI score
SaveExploits0
Kitploit
Kitploit
added 2026/08/27 1:22 a.m.5 views

hush

AI 에이전트 보안 규칙을 위한 이식 가능한 오픈 사양 사양 · 문서 · 규칙 세트 · JSON Schema HushSpec은 AI 에이전트 보안 규칙을 위한 오픈 정책 형식입니다. 파일 시스템 접근, 네트워크 이그레스, 도구 사용, 시크릿 탐지 등을 포함하여 에이전트가 런타임에 무엇을 할 수 있는지 정의하지만, 그러한 통제가 어떻게 적용되어야 하는지는 규정하지 않습니다. 이러한 분리를 통해 정책은 런타임, 프레임워크, 언어를 넘어 이식이 가능합니다. v0.1.1-alpha — 핵심 사양, 4개 SDKRust,...

5.4AI score
SaveExploits0References2
Kitploit
Kitploit
added 2026/08/27 1:13 a.m.5 views

sigma-ai

AgentShield Sigma 규칙 이 저장소는 무엇인가요? 이 저장소는 AI 에이전트가 공격받거나 조작될 때 이를 식별하는 데 도움이 되는 탐지 규칙을 포함하고 있습니다. 일종의 "위협 시그니처" 라이브러리로 생각하면 됩니다. 각 규칙은 에이전트의 로그 데이터와 일치할 때 의심스러운 무언가가 발생하고 있음을 알리는 패턴을 설명합니다. AgentShield는 AI 에이전트를 위한 오픈 소스 보안 계층입니다. 실시간으로 에이전트 동작을 모니터링하고 이러한 Sigma 규칙을 사용하여 프롬프트 인젝션, 데이터 도난, 도구 중독, ...

5.6AI score
SaveExploits0References4
Kitploit
Kitploit
added 2026/08/27 12:48 a.m.2 views

MakerChecker

🛡️ MakerChecker AIエージェント向けオープンソースのセキュリティレイヤー。 デフォルト拒否による強制、人間による承認、暗号署名された監査証跡 — エージェントは許可された操作のみを実行し、自身の作業を承認できないことを証明可能 にします。 ウェブサイト · ライブデモ · mc scan · ドキュメント あなたのエージェントは、既存のフレームワーク(LangChain、Claude SDK、CrewAI)でそのまま動作し続けます。MakerCheckerは、すべてのツール呼び出しの前にチェックポイントとして、後ろには署名付き台帳として配置されます。エージェントはロール...

5.5AI score
SaveExploits0References24
Kitploit
Kitploit
added 2026/08/26 11:40 p.m.3 views

tealtiger

TealTiger SDK de Segurança e Governança para Agentes de IA Governança determinística, proteções, rastreamento de custos e gerenciamento de políticas para aplicações LLM. Código aberto. TypeScript + Python. Funciona com qualquer provedor...

5.3AI score
SaveExploits0References2
Kitploit
Kitploit
added 2026/08/26 11:38 p.m.3 views

wardgate

Wardgate - Gateway di Sicurezza per Agenti AI Wardgate è un gateway di sicurezza che si pone tra gli agenti AI e il mondo esterno -- isolando le credenziali per le chiamate API, isolando le chiavi SSH per l'esecuzione remota di comandi, e controllando l'esecuzione dei comandi in ambienti remoti...

5.4AI score
SaveExploits0References14
Kitploit
Kitploit
added 2026/08/26 11:23 p.m.2 views

Agent-Security-Regression-Harness

OWASP Agent Security Regression Harness L'OWASP Agent Security Regression Harness è un test harness open source e indipendente dal fornitore, progettato per eseguire scenari di regressione di sicurezza riproducibili su applicazioni agente e sistemi integrati con MCP. Il progetto aiuta sviluppator...

5.3AI score
SaveExploits0
Kitploit
Kitploit
added 2026/08/26 10:07 p.m.3 views

node9-proxy

🛡️ Node9 Cosa ha fatto davvero il tuo agente AI? Scoprilo. Node9 si posiziona tra il tuo agente AI e gli strumenti che può usare — scopri cosa ha già fatto, proteggiti dalle azioni rischiose in tempo reale e rivedi cosa è successo in qualsiasi finestra temporale. Funziona con Claude Code · Codex...

5.5AI score
SaveExploits0
Kitploit
Kitploit
added 2026/08/26 9:17 p.m.3 views

sage

Sage Sicurezza per gli Agenti — Rilevamento e Risposta per assistenti di codifica AI Sage è un leggero strato di sicurezza che protegge gli agenti AI dall'esecuzione di azioni pericolose. Intercetta le chiamate degli strumenti — comandi shell, recupero URL, scritture di file — e le verifica...

5.4AI score
SaveExploits0References2
Kitploit
Kitploit
added 2026/08/25 4:32 a.m.4 views

aegisagent

AegisAgent — AI Agent Runtime Security Gateway Gateway di sicurezza runtime per AI Agent: legame crittografico di ogni chiamata di strumento alla reale completazione del modello, esecuzione di policy zero-trust, isolamento in sandbox e approvazione umana in un'unica soluzione. Contesto: perché...

5.4AI score
SaveExploits0References6
ATTACKERKB
ATTACKERKB
added 2026/08/17 4:29 p.m.14 views

CVE-2026-40145

A vulnerability exists in the interaction between a Endpoint Privilege Management Windows Deployment support utility and the agent's tamper protection controls. Under certain conditions, the protections applied to the utility process may not be enforced as intended...

7.1CVSS5.3AI score0.00127EPSS
SaveExploits0References3
AlpineLinux
AlpineLinux
added 2026/06/24 1:20 p.m.33 views

CVE-2026-57282

Jenkins Git client Plugin 6.6.0 and earlier does not correctly escape the workspace directory name when it is embedded into a generated SSH wrapper script, allowing attackers able to control the name of a build's working directory to execute arbitrary operating system commands on the agent...

5CVSS6.1AI score0.00253EPSS
SaveExploits0References1
GithubExploit
GithubExploit
added 2026/06/01 10:12 a.m.114 views

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

6.5AI score
SaveExploits0
HackRead
HackRead
added 2026/05/19 9:13 p.m.25 views

AI Agent Security: Automating Workflow Without Creating Prompt Injection or Data Leak Risks

AI agent security starts with a simple fact: the more authority an agent has, the tighter its access…...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/05/18 12:00 a.m.23 views

Agent Security Is a Systems Problem

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness the dominant viewpoint...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/25 12:00 a.m.13 views

Architecture Matters for Multi-Agent Security

Multi-agent systems MAS, composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual agents exhibit robust security, architectural decisions...

5.4AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/25 12:00 a.m.54 views

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...

5.7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/09 12:00 a.m.6 views

Towards Modeling Cybersecurity Behavior of Humans in Organizations

We undertake a comprehensive and structured synthesis of the drivers of human behavior in cybersecurity, focusing specifically on people within organizations i.e., especially employees in companies, and integrate key concepts such as awareness, security culture, and usability into a coherent...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/06 12:00 a.m.10 views

Targeted Bit-Flip Attacks on LLM-Based Agents

Targeted bit-flip attacks BFAs exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models e.g., image classifiers, LLM-based agents with multi-stage pipelines and external tools present new attack surfaces,...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/02 12:00 a.m.15 views

Extending the Formalism and Theoretical Foundations of Cryptography to AI

Recent progress in Large Language Models LMs has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant autonomy and authority. The security community has been...

5.9AI score
SaveExploits0
Rows per page
Query Builder