sentinel-mcp

SentinelMCP — AI驱动的网络防御系统 Google Cloud Hackathon 提交项目 — 由 Google Cloud Agent Builder Vertex AI Agent 编排的自主威胁检测与响应，基于 Gemini 2.0 Flash、模型上下文协议（MCP）和 Dynatrace 可观测性。 问题所在 安全团队在处理典型安全事件时，平均检测时间（MTTD）为 30分钟 ，平均修复时间（MTTR）为 4小时 。等到人工分析师检测到攻击、编写防火墙规则并部署完毕，损失早已造成。 解决方案 SentinelMCP 将 MTTD 缩短至 30秒，MTTR 缩短至...

EUVD-2006-1243

Malware in sbrugna...

MAJIC: Markovian Adaptive Jailbreaking Via Iterative Composition of Diverse Innovative Strategies

Large Language Models LLMs have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating the input prompts. Existing black-box jailbreaking techniques primarily rely on static prompts crafted with a single,...

Cross site scripting

Cross-site scripting XSS vulnerability in issue/createissue.aspx in Gemini 2.0 allows remote attackers to inject arbitrary web script or HTML via the rtcDescription$RadEditor1 field. NOTE: the provenance of this information is unknown; the details are obtained solely from third party information...

CVE-2006-1239

Cross-site scripting XSS vulnerability in issue/createissue.aspx in Gemini 2.0 allows remote attackers to inject arbitrary web script or HTML via the rtcDescription$RadEditor1 field. NOTE: the provenance of this information is unknown; the details are obtained solely from third party information...

CVE-2006-1239

Cross-site scripting XSS vulnerability in issue/createissue.aspx in Gemini 2.0 allows remote attackers to inject arbitrary web script or HTML via the rtcDescription$RadEditor1 field. NOTE: the provenance of this information is unknown; the details are obtained solely from third party information...

CVE-2006-1239

The CVE-2006-1239 entry describes a Cross-site scripting (XSS) vulnerability in Gemini 2.0, specifically in issue/createissue.aspx where an attacker can inject arbitrary script via the rtcDescription$RadEditor1 field. The issue is confirmed by NVD data with a CVSSv2 base score of 4.3 (MEDIUM) and...