67 matches found
sigma-ai
AgentShield Sigma ê·ì¹ ìŽ ì ì¥ìë 묎ììžê°ì? ìŽ ì ì¥ìë AI ììŽì ížê° 공격ë°ê±°ë ì¡°ìë ë ìŽë¥Œ ìë³íë ë° ëììŽ ëë íì§ ê·ì¹ì í¬íšíê³ ììµëë€. ìŒì¢ ì "ìí ìê·žëì²" ëŒìŽëžë¬ëŠ¬ë¡ ìê°í멎 ë©ëë€. ê° ê·ì¹ì ììŽì ížì ë¡ê·ž ë°ìŽí°ì ìŒì¹í ë ìì¬ì€ë¬ìŽ ë¬Žìžê°ê° ë°ìíê³ ììì ì늬ë íšíŽì ì€ëª í©ëë€. AgentShieldë AI ììŽì ížë¥Œ ìí ì€í ìì€ ë³Žì ê³ìžµì ëë€. ì€ìê°ìŒë¡ ììŽì íž ëìì 몚ëí°ë§íê³ ìŽë¬í Sigma ê·ì¹ì ì¬ì©íì¬ í롬ííž ìžì ì , ë°ìŽí° ëë, ë구 ì€ë , ...
hush
ììŽì ížìê² ìœì ì ìë 겜ê³ë¥Œ ë¶ì¬íìžì. ê²ìŠí ì ìë ê²°ì ì ì»ìŒìžì. ê°ì · ë¹ ë¥ž ìì · ìë ë°©ì · SDK · CLI · ì ì± Â· 묞ì · ëª ìž HushSpecìŽë? HushSpecì AI ììŽì ížê° ìëíë 볎ì ì ìŽì ëí ê³µê° ëª ìžì ëë€. YAMLë¡ ì ì± ì ìì±íê³ Rust, TypeScript, Python ëë Goë¡ íê°íì¬ ê° ê²°ì ì ê·ž ë€ì ìë ì ì± ê³Œ ì°ê²°íë ìììŠì ìì±íìžì. ììŽì ížê° ì€ì ë¡ ë€ë£šë ê²ë€âíìŒ, ë€ížìí¬, ì ž, ë구, ëžëŒì°ì , ìœë ì€íâì ë€ë£¹ëë€. ëª ìžë ê·ì¹ê³Œ ê·ž...
MakerChecker
ð¡ïž MakerChecker AI ììŽì ížë¥Œ ìí ì€íìì€ ë³Žì ê³ìžµ. Ʞ볞 ê±°ë¶deny-by-default ì ì©, ì¬ë ì¹ìž, ìížíì ìŒë¡ ìëª ë ê°ì¬ ì¶ì â ììŽì ížê° ë¶ì¬ë ìì ë§ ì€ííê³ ìì ì ìì ì ìŠëª ê°ë¥íê² ì¹ìží ì ìëë¡ í©ëë€. ì¹ì¬ìŽíž · ëŒìŽëž ë°ëªš · mc scan · 묞ì ììŽì ížë Ʞ졎 íë ììí¬LangChain, Claude SDK, CrewAIìì ê³ì ì€íë©ëë€. MakerCheckerë 몚ë ë구 ížì¶ ìì 첎í¬í¬ìžížë¡, ë€ìë ìëª ë ìì¥ìŒë¡ ìì¹í©ëë€. ììŽì ížë ìí ì íµíŽìë§...
Agent-Security-Regression-Harness
OWASP Agent Security Regression Harness OWASP Agent Security Regression Harnessã¯ããšãŒãžã§ã³ãã£ãã¯ã¢ããªã±ãŒã·ã§ã³ãšMCPçµ±åã·ã¹ãã ã«å¯ŸããŠå®è¡å¯èœãªã»ãã¥ãªãã£ååž°ã·ããªãªãå®è¡ããããã®ããªãŒãã³ãœãŒã¹ã§ãã³ããŒäžç«ã®ãã¹ãããŒãã¹ã§ãã ãã®ãããžã§ã¯ãã¯ããã«ããŒãšãã£ãã§ã³ããŒããããã³ãããã¢ãã«ãããŒã«ãæ€çŽ¢ãœãŒã¹ãã¡ã¢ãªãæ¿èªãããŒããŸãã¯MCPçµ±åãžã®å€æŽããæ¢ç¥ã®ã»ãã¥ãªãã£é害ãåå°å ¥ããªãããšãæ€èšŒããã®ã«åœ¹ç«ã¡ãŸãã ãã®ãããžã§ã¯ãã®æ©èœ...
tealtiger
TealTiger AI ììŽì íž ë³Žì ë° ê±°ë²ëì€ SDK LLM ì í늬ìŒìŽì ì ìí ê²°ì ë¡ ì ê±°ë²ëì€, ê°ëë ìŒ, ë¹ì© ì¶ì , ì ì± êŽëЬ. ì€íìì€. TypeScript + Python. 몚ë ê³µêžìì íží. ì¹ì¬ìŽíž · 묞ì · ìì · ëì€ìœë · êž°ì¬íêž° â¡ 60ìŽ íµì€ííž ì€ì¹: npm install tealtiger ëë pip install tealtiger, ê·žë° ë€ì Ʞ졎 OpenAI ížì¶ íë륌 ê°ìžììì€:typescript import TealOpenAI from 'tealtiger'; const client...
sage
Sage ãšãŒãžã§ã³ãã®å®å šæ§ â AIã³ãŒãã£ã³ã°ã¢ã·ã¹ã¿ã³ãã®ããã®ãšãŒãžã§ã³ãæ€åºïŒå¯Ÿå¿ Sageã¯ãAIãšãŒãžã§ã³ããå±éºãªã¢ã¯ã·ã§ã³ãå®è¡ããã®ãé²ã軜éã»ãã¥ãªãã£ã¬ã€ã€ãŒã§ããã·ã§ã«ã³ãã³ããURLååŸããã¡ã€ã«æžã蟌ã¿ãªã©ã®ããŒã«åŒã³åºããã€ã³ã¿ãŒã»ããããå®è¡åã«è€æ°ã®è åšæ€åºã¬ã€ã€ãŒã§ãã§ãã¯ããŸãã æ³šé: Sageã¯ã€ã³ã¹ããŒã«æ¹æ³ã«ãã£ãŠç°ãªã補ååïŒäŸïŒNorton SageãAvast SageïŒã§è¡šç€ºãããå ŽåããããŸãã詳现ã¯ãã©ã³ãã£ã³ã°ãåç §ããŠãã ããã äž»ãªæ©èœ URLã¬ãã¥ããŒã·ã§ã³ â ãã«ãŠã§ã¢ããã£ãã·ã³ã°ãè©æ¬ºURLã®ã¯ã©ãŠãããŒã¹æ€åº...
wardgate
Wardgate - AI ììŽì íž ë³Žì ê²ìŽížìšìŽ Wardgate ë AI ììŽì ížì ìžë¶ ìžê³ ì¬ìŽì ìì¹íë 볎ì ê²ìŽížìšìŽì ëë€. API ížì¶ì© ì격 ìŠëª ì 격늬íê³ , ì격 ëª ë ¹ ì€íì© SSH í€ë¥Œ 격늬íë©°, ì격 í겜íŽë ìŽëžììì ëª ë ¹ ì€íì ì ìŽí©ëë€. AI ììŽì ížìê² API, SSH í€, ì ž ë구ì ëí ì¡ìžì€ ê¶íì ë¶ì¬íë, ì격 ìŠëª ì ì§ì ì ê³µíê±°ë ì§ì ì€íì ì 뢰íì§ ìê³ ë ì¬ì©í ì ììµëë€. 묞ì ì AI ììŽì ížë ê°ë ¥í©ëë€. ìŒì êŽëЬ, ìŽë©ìŒ íìž, ìì ì ë°ìŽíž, ìœë ìì±, ì¶ì ìëí ë±ìŽ...
node9-proxy
ð¡ïž node9 Access control for AI agents Your AI agents can reach Slack, GitHub, email, and your database. node9 decides what they may do with each one. Credential jail · secrets and PII · destructive git, SQL and shell held for review · MCP tool pinning · network egress allowlist · loop breaker · on...
secure-agent-playbook
Secure Agent Playbook AI ììŽì ížë¥Œ ìí ì€íìì€ ë³Žì íë ìŽë¶ì ëë€. ììŽì ížê° ìœë 늬뷰ë¶í° AI ììŽì íž ë³Žì ê°ì¬ê¹ì§ 볎ì ìì§ëìŽë§ ìì ì ìíí ì ìëë¡ íë, OWASPì êž°ë°í 구조íë ì 찚륌 ì ê³µí©ëë€. 목찚 ì ì¬ì©íŽìŒ íëê°? ìŽê²ì 묎ììžê° ë¹ ë¥ž ìì ì€í¬ 칎íë¡ê·ž ììŽì íž ì¶ë ¥ ìì íë ìŽ ìí€í ì² OWASP ì¬ëš êŽë š íë¡ì íž êž°ì¬íêž° ì ì¬ì©íŽìŒ íëê°? íë ìŽë¶ ììŽ AI ììŽì ížìê² "ëŽ ìœë륌 볎ì êŽì ìì ê²í íŽì€"ëŒê³ ìì²í멎 í멎ì ìž ì²Ží¬ëЬì€ížë§ ë°ê² ë©ëë€. ìŽ...
aegisagent
AegisAgent â AI Agent ã©ã³ã¿ã€ã ã»ã»ãã¥ãªãã£ã²ãŒããŠã§ã€ AI Agent ã©ã³ã¿ã€ã ã»ã»ãã¥ãªãã£ã²ãŒããŠã§ã€ â åããŒã«åŒã³åºããå®éã®ã¢ãã«è£å®ã«æå·åŠçã«ãã€ã³ããããŒããã©ã¹ãããªã·ãŒå®è¡ããµã³ãããã¯ã¹åé¢ã人éã«ããæ¿èªãäžäœåã èæ¯ïŒãªã AegisAgent ãå¿ èŠãªã®ã 2026幎8æãCloud Security Alliance 㯠CoreBreak è匱æ§ãã¡ããªãŒ ãå ¬éããŸããããã®äžé£ã®æ·±å»ãªè匱æ§ã¯ãAI Agent ãšã³ã·ã¹ãã ã®ã»ãã¥ãªãã£åæãå®å šã«æã¡ç ŽããŸããïŒ CVE çªå·| 圱é¿ã³ã³ããŒãã³ã| ãªã¹ã¯ã®èª¬æ...
Ajar
Ajar: ãšãŒãžã§ã³ãé²åŸ¡ã«ãããéæŸç¹æš©ã®æž¬å® ãšãŒãžã§ã³ãã»ãã¥ãªãã£ã®ãã³ãããŒã¯ã¯ãæ»ææåçãšè¯æ§ãŠãŒãã£ãªãã£ãšãã2ã€ã®æ°å€ãå ±åããããã©ã¡ããå®éã«è¡ãããå®è¡ããèªã¿åããããã®ã§ãããã©ã¡ãããå®è¡ãããªãã£ãçµè·¯ã«ãããŠé²åŸ¡ãäœãèš±å¯ããçšæããã£ããã瀺ããŠã¯ããªããAjarã¯ãããçŽæ¥åãããããåè¯æ§ã¿ã¹ã¯ã«ã€ããŠããã®ã¿ã¹ã¯ã«ã¯äžèŠãªåè£ããŒã«åŒã³åºããæ§ç¯ãããšãŒãžã§ã³ããè¡åãåŸãããããæç¹ã§ååè£ãé²åŸ¡ã«æç€ºããé²åŸ¡ãèš±å¯ããæå®³åºŠã§éã¿ä»ãããå²åãã¹ã³ã¢åããã Ajarã¯æ¢åã®ãã³ãããŒã¯ã«æ¥ç¶ãããã®ãã³ãããŒã¯ãæ¢ã«ä¿æããŠãããã® â...
DROS-VEP-lite
ð¡ïž VEP: ãªãŒãã³ãšãŒãžã§ã³ãã»ãã¥ãªãã£ç ç©¶ãã¹ãããã 䟵害åŸããã³ãã£ãžã«ã«AIç ç©¶ã®ããã®ãã³ã³ããŒã¶ãã«ãªã·ã¹ãã ã¬ãã«è©äŸ¡åºç€ ãVEPïŒVulnerability & Exploitability ProtocolïŒã¯ããšãŒãžã§ã³ãã®ã»ãã¥ãªãã£å¶åŸ¡ã䟵害åŸãæå¹ã§ããç¶ããããç¹ã«ãšãŒãžã§ã³ãã®èªå¯ãšå®éã®ã·ã¹ãã å®è¡ã®å¢çã«ãããŠããããå€å®ããããã®ãªãŒãã³ã§å®è£ éäŸåã®ç ç©¶è©äŸ¡ç°å¢ã§ããDROS-VEP...
clawguard
ðŠ ClawGuard v3 ãšã³ã¿ãŒãã©ã€ãºAIãšãŒãžã§ã³ãã»ãã¥ãªãã£ããŒã«ããã - SKILL.mdé§ååã¢ã¯ãã£ããã£ãã§ã³ã¹ æ žå¿ç念 ClawGuard v3ã®é²åŸ¡ã®äžæ žã¯ã³ãŒãã§ã¯ãªããSKILL.mdã«ãããŸãïŒ åã¢ãžã¥ãŒã«ã®SKILL.mdèªäœãå®å šãªé²åŸ¡ã¬ã€ãã§ãïŒ ãšãŒãžã§ã³ãã«ãã€ããªã¬ãŒããã ãæç€º ãšãŒãžã§ã³ãã«ã©ã®ããã«æ€åºããã ãã¬ã€ã å ·äœçãªæ€åºãã¿ãŒã³ãšã«ãŒã« ãæäŸ åºå圢åŒãšå€æåºæº ãå®çŸ© ã³ãŒãã¹ã¯ãªããã¯è£å©ããŒã«ã«éãããæ¬åœã®ç¥æ§ã¯SKILL.mdã«ãããŸãã ð¯ 5ã€ã®ã»ãã¥ãªãã£ã¢ãžã¥ãŒã« ã¢ãžã¥ãŒã«| äœçœ®|...
AI Agent Security Readiness: The Federal Standard You Should Get Ahead Of
Here's the uncomfortable part first: in August 2026, researchers found AI agents connected to Hugging Face running loose inside enterprise networks. No owner, no audit trail, nobody who could tell you they existed until something broke. If that sentence made your stomach drop a little, good,...
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...
The Anatomy of a Prompt Injection: A Component Model for Structured Analysis
Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis. This paper formaliz...
dugganusa-ietf â Updated!
DugganUSA â IETF Hackathon Contributions Real-world threat-intelligence contributions from DugganUSA LLC to the IETF Hackathon, offered to project champions as empirical grounding for standards work. We are a bootstrapped threat-intelligence shop. We run a public STIX 2.1 feed, an edge-blocking...
Exploit for Origin Validation Error in Ultraviolet Cocos_Ai
DugganUSA â IETF Hackathon Contributions Real-world threat-in...
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...