Security researchers have found nearly 3000 publicly visible Google API keys authorizing Gemini. This allows abusive access.

Researchers with Truffle Security are warning that old and seemingly benign Google API keys might now be weaponized by threat actors after gaining Gemini AI authorization permissions, in a destructive ...

Probably not an isolated incident only as researchers have already found 2,863 live API keys exposed A developer says their company is on the hook for more than $82,000 in unauthorized charges after a ...

API key exploitation is more than hypothetical. In a different context, a student who reportedly exposed a GCP API key on GitHub last June was left nursing a $55,444 bill (later waived by Google) ...

Source Code Exfiltration in Google Antigravity‍TL;DR: We explored a known issue in Google Antigravity where attackers can silently exfiltrate proprietary source codeBy hiding malicious instructions ...

A developer-targeting campaign leveraged malicious Next.js repositories to trigger a covert RCE-to-C2 chain through standard ...

Safe coding is a collection of software design practices and patterns that allow for cost-effectively achieving a high degree ...

フリー （ ⁠株⁠ ） は2026年3月2日、同社のサービス 「freee」 で提供されているAPIをAIエージェントが直接操作できるMCPサーバー 「freee-mcp」 をオープンソースとして公開した。

AI搭載のコーディングアシスタントClaude Codeに発見された脆弱性により、悪意あるリポジトリ設定ファイルを通じたリモートコード実行とAPI認証情報の窃取が可能に サイバーセキュリティソリューションのパイオニアであり、世界的リーダーであるチェック・ポイント・ソフトウェア・テクノロジーズ（ ...

OpenClaw’s autonomy amplifies convenience into risk: inbox loss, trade-secret leakage, clawphishing exposure, plaintext keys, and malware skills.

An AI assistant can quickly turn into a malicious insider, so be careful with permissions.

AI agents are all the rage – though they’re just getting off the ground ...