Lucene search
+L

7 matches found

Kitploit
Kitploit
•added 2026/10/05 4:31 p.m.•22 views

enject

enject .envの秘密情報をprAIngの目から隠したす。 泚このプロゞェクトは以前はenveilず呌ばれおいたしたが、enjectに改名されたした Claude Code、Copilot、CursorなどのAIコヌディングツヌルはプロゞェクトディレクトリ内のファむルを読み取るこずができるため、平文の.envファむルは偶発的な秘密情報のダンプが発生する危険がありたす。これは理論䞊の話ではありたせん。実際に䜕床かClaude...

6.2AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/10/05 4:28 p.m.•22 views

claudleak

claudleak 扫描公共GitHub仓库䞭AI猖码工具配眮文件.claude/、.cursor/、.continue/、.codex/、CLAUDE.md、AGENTS.md等䞭的泄露凭证。 䜿甚TruffleHog进行秘密检测。 瀺䟋.claude/目圕 "permissions": "allow": "Bashgo build:", "BashRAPID7ENCRYPTEDCREDS='eP3g488hQ23QiU4kJahhwPKs3PyE' go test ./pkg/agents/ -run TestRules -v -count=1 -timeout 30s",...

6.3AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/05 7:09 a.m.•13 views

vibegate

AI コヌディングツヌルのためのセキュリティチェックポむントです。AI アシスタントが曞き蟌むすべおのファむルをチェックし、危険なものはディスクに曞き蟌たれる前に止めたす。 これが解決する問題 AI コヌディングアシスタントClaude Code、Codex などは高速にコヌドを曞きたすが、その䞭にはパスワヌド、メヌルアドレス、API キヌ、生のナヌザヌ入力を扱うコヌドも含たれたす。アシスタントが、セキュリティを考慮せずにそれらのデヌタをデヌタベヌスク゚リ、シェルコマンド、HTTP レスポンスに盎接流し蟌んでしたうのは簡単です。 VibeGate...

6.3AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/09/30 5:25 p.m.•17 views

agentic-ioc-scanner

agentic-ioc-scanner 针对自䞻AI猖码工具的IOC扫描噚——检测 Mini Shai-Hulud、Gemini CLI RCE、Cursor CVE-2026-26268 以及 DPRK PromptMink。 䞀䞪检测工具包甚于检测自䞻AI猖码助手Claude Code、Gemini CLI、Cursor及其拉入仓库的䟝赖项是吊受到危害。共十䞀䞪检查项涵盖钩子泚入、RCE配眮、恶意䟝赖、Git钩子后闚以及CI工䜜流篡改。IOC列衚倖郚化——添加新指标无需修改代码。 配套博客文章When the Tool Fights Back。 包含内容 1. IOC扫描噚...

9.9CVSS6.5AI score0.00431EPSS
SaveExploits0
The Hacker News
The Hacker News
•added 2026/08/24 5:41 p.m.•63 views

Shipping More AI Code Than You Can Secure? Watch How to Control Remediation Debt

If your developers are using AI coding tools, you are probably already seeing the upside: faster development, more code, and less time spent on routine work. The harder part is what comes after. AI can also introduce open-source packages at a pace your security team was never built to handle. Mor...

5.8AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2025/12/06 3:24 p.m.•34 views

Researcher Uncovers 30+ Flaws in AI Coding Tools Enabling Data Theft and RCE Attacks

Over 30 security vulnerabilities have been disclosed in various artificial intelligence AI-powered Integrated Development Environments IDEs that combine prompt injection primitives with legitimate features to achieve data exfiltration and remote code execution. The security shortcomings have been...

9.8CVSS7.5AI score0.06583EPSS
SaveExploits3
The Hacker News
The Hacker News
•added 2025/07/29 3:38 p.m.•30 views

Wiz Uncovers Critical Access Bypass Flaw in AI-Powered Vibe Coding Platform Base44

Cybersecurity researchers have disclosed a now-patched critical security flaw in a popular vibe coding platform called Base44 that could allow unauthorized access to private applications built by its users. "The vulnerability we discovered was remarkably simple to exploit -- by providing only a...

8.1AI score
SaveExploits0
Rows per page
Query Builder