Lucene search
+L

3 matches found

Kitploit
Kitploit
•added 2026/10/03 8:23 a.m.•44 views

duo-agentflow-auditor

Duo AgentFlow Auditor AIコードセキュリティ — SASTが見逃す脆弱性をAI生成コードから検出 GitLab Duo Agent プラットフォーム上に構築 AI生成コードの40〜62%にセキュリティ脆弱性が含まれています。 従来のSASTはCVEを検出します。私たちはSASTが見逃すもの — プロンプトインジェクション、LLM出力実行、安全でないMLデシリアライゼーションを検出します。 はじめに · アーキテクチャ · 検出ルール · セットアップガイド · 実装 問題点 AIはコード生成を加速させる一方で、新たなセキュリティのボトルネックを生み出します: 課題|...

6.3AI score
SaveExploits0References4
Packet Storm News
Packet Storm News
•added 2026/06/14 12:00 a.m.•46 views

Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?

We ran 300 repeated vulnerability-finding scans to measure how repeatable agentic large language model LLM security review is on the same JavaScript code, prompt, and benchmark harness. The headline result is that LLM security findings were unevenly repeatable: reference-matched findings were...

5.4AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/02/24 6:04 a.m.•20 views

Anthropic Says Chinese AI Firms Used 16 Million Claude Queries to Copy Model

Anthropic on Monday said it identified "industrial-scale campaigns" mounted by three artificial intelligence AI companies, DeepSeek, Moonshot AI, and MiniMax, to illegally extract Claude's capabilities to improve their own models. The distillation attacks generated over 16 million exchanges with...

6.2AI score
SaveExploits0
Rows per page
Query Builder