security-lab https://blog.hatena.ne.jp/security-lab/ TT 脆弱性 Blog https://vul.hatenadiary.com/ AI: Claude Mythos ツール: curl 【要点】 ◎Mythosはcurl解析で5件中1件のみ低リスク脆弱性、AI脆弱性発見能力は過大評価の可能性 (Security Affairs) 190 <iframe src="https://hatenablog-parts.com/embed?url=https%3A%2F%2Fvul.hatenadiary.com%2Fentry%2F2026%2F05%2F12%2F000000_1" title="The world’s most “Dangerous” AI, Anthropic’s Mythos, found only one flaw in curl - TT 脆弱性 Blog" class="embed-card embed-blogcard" scrolling="no" frameborder="0" style="display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;"></iframe> Hatena Blog https://hatena.blog 2026-05-12 00:00:00 rich https://vul.hatenadiary.com/entry/2026/05/12/000000_1 1.0 100%