Lucene search
+L

1604 matches found

Kitploit
Kitploit
•added 2026/09/28 5:03 p.m.•10 views

SecOPD

SecOPD: オンポリシー蒸留による適応型プロンプトインジェクションの軽減 Yibo Peng · Long Lian · David Wagner† · Sizhe Chen† † 共同指導。 論文 プロジェクトページ モデル このリリースは、論文の最終的なfull-response KL 定式化を実装したものであり、 no-parsing バリアントとも呼ばれます。生徒モデルは攻撃されたコンテキスト下で ロールアウトします。同じベースモデルから初期化されたクリーンコンテキストの教師モデルが、 ペアとなるクリーンコンテキスト下で生徒モデルのサンプリングされたトークンをスコアリングしま...

6.2AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/09/28 3:36 p.m.•13 views

CVE-2025-54794-Hijacking-Claude-AI-with-a-Prompt-Injection-The-Jailbreak-That-Talked-Back

🧠 CVE-2025-54794: Claude AIをプロンプトインジェクションで乗っ取る – 逆切れした脱獄 By Aditya Bhatt | オフェンシブセキュリティスペシャリスト | レッドチームオペレーター | VAPT中毒者 ⚔️ はじめに: AIが言葉でハックされる時代 言語モデルがコード、コンテンツ、思考の副操縦士となった現代、脆弱性はもはやポートやペイロードだけの話ではありません。それは言葉 の問題なのです。 CVE-2025-54794 は、CVEアーカイブの中の単なる番号ではありません。それは次のような声明です。 「最も先進的なAIでも、適切なささやきで操作されうる...

9.1CVSS8.1AI score0.01357EPSS
SaveExploits0
Kitploit
Kitploit
•added 2026/09/28 1:44 p.m.•10 views

clawguard

🦞 ClawGuard v3 エンタープライズAIエージェントセキュリティツールキット - SKILL.md駆動型アクティブディフェンス 核心理念 ClawGuard v3の防御の中核はコードではなく、SKILL.mdにあります! 各モジュールのSKILL.md自体が完全な防御ガイドです: エージェントにいつトリガーするか を指示 エージェントにどのように検出するか をガイド 具体的な検出パターンとルール を提供 出力形式と判断基準 を定義 コードスクリプトは補助ツールに過ぎず、本当の知性はSKILL.mdにあります。 🎯 5つのセキュリティモジュール モジュール| 位置|...

6.2AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/09/28 12:44 p.m.•6 views

ai-ctf

ai-ctf プロンプトインジェクションに不慣れな技術者向けのガイド付きレッスンを備えた、ローカルのAI Capture-the-Flag 。プレイヤーは6つのAIペルソナ(1つは隠し)を探索し、プロンプトインジェクション、ツール呼び出しの悪用、ビジネスロジックの操作、サプライチェーンのフィンガープリンティング、Web偵察、OSINTを通じて20個のフラグを保護することもできる。...

6.3AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/09/28 11:03 a.m.•13 views

ROPE

ROPE: Routed Origin Policy Enforcement 本論文のソースコード: ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection by Xinhang Ma, Chaowei Xiao, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik 概要...

6.2AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/09/28 7:14 a.m.•15 views

CVE-2025-64495-POC

CVE-2025-64495-POC Open WebUI は、'Insert Prompt as Rich Text'(プロンプトをリッチテキストとして挿入)が有効な場合、プロンプトを介して保存型 DOM XSS に対して脆弱であり、ATO/RCE を引き起こします。 概要 カスタムプロンプトをチャットウィンドウに挿入する機能は、'Insert Prompt as Rich Text' が有効な場合、プロンプト本文がサニタイズなしで DOM シンク .innerHtml に割り当てられるため、DOM XSS...

8.7CVSS8.5AI score0.0046EPSS
SaveExploits2
Kitploit
Kitploit
•added 2026/09/28 5:44 a.m.•12 views

sk-cve-2026-26030-lab

CVE-2026-26030 — Semantic Kernel フィルター eval RCE ラボ CVE-2026-26030 を再現する自己完結型ラボ:Microsoft Semantic Kernel Python, 倫理的ラボのみ。専用の virtualenv 内で隔離されています;ペイロードは無害です(ヘッドレス PoC では touch マーカーファイル、UI デモでは open -a Calculator)そして自分自身の非特権ユーザーとして実行されます。 Setup ./setup.sh builds two isolated venvs 1.39.3...

9.9CVSS6.4AI score0.03703EPSS
SaveExploits2
Packet Storm News
Packet Storm News
•added 2026/09/27 12:00 a.m.•6 views

When Consent Outlives Context: Residual Authority Replay in Long-Lived Agents

LLM agents increasingly rely on user approval to authorize security-sensitive actions at runtime. Such approvals are granted within a specific task and execution context. In long-lived agents, authorization decisions may need to persist across tasks or sessions. We find that this continuity can...

6AI score
SaveExploits0
EUVD
EUVD
•added 2026/09/26 12:31 a.m.•16 views

EUVD-2025-26607

Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox, enforced by smolagents. The attack requires a Prompt Injection in order to trick the agent to create malicious code...

7.6CVSS6.7AI score0.00312EPSS
SaveExploits0References3
Packet Storm News
Packet Storm News
•added 2026/09/25 12:00 a.m.•10 views

MetaPermit: Scalable and Auditable Access Control for AI Agents Via LLM-Inferred Meta-Attributes

The rise of autonomous AI agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to adversarial manipulation through Indirect Prompt Injection IPI attacks. In practice, deployed agent systems such as OpenAI Codex and Claude Code protect tool...

5.6AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/09/25 12:00 a.m.•10 views

Crypto-Bound Identity-Verified Capability Tokens for Coordinating Distributed AI Agents: A Proposal

The prospect of fully autonomous transactional agents did not appear on the horizon until the advent of high capability language models. With such models, the operational benefits of adaptive task orchestration and independent but constrained decision making are tantalizing for enterprises and...

5.8AI score
SaveExploits0
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/24 12:00 a.m.•7 views

CVE-2026-61732: Improper Neutralization of Special Elements in Output Used by a Downstream Component

Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users...

10CVSS6.1AI score0.01221EPSS
SaveExploits1References2
The Hacker News
The Hacker News
•added 2026/09/23 11:47 a.m.•33 views

Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence AI companies noting that they are continuing to invest in improving alignment to combat risky behavior. Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to...

5.5AI score
SaveExploits0
Github Security Blog
Github Security Blog
•added 2026/09/22 8:35 p.m.•14 views

MCP Atlassian: Arbitrary local file READ via unconstrained file_path in upload_attachment (Confluence + Jira)

Summary This is an arbitrary local file READ vulnerability on the Confluence and Jira uploadattachment tool paths. It's the symmetric counterpart of the file-write vulnerability you patched as CVE-2026-27825. The write direction was fixed; the read direction was left open. Reporter: Sean Valentin...

8.3CVSS6.1AI score0.00349EPSS
SaveExploits1References6Affected Software1
OSV
OSV
•added 2026/09/22 8:35 p.m.•11 views

GHSA-F4P7-QX46-WC5J MCP Atlassian: Arbitrary local file READ via unconstrained file_path in upload_attachment (Confluence + Jira)

Summary This is an arbitrary local file READ vulnerability on the Confluence and Jira uploadattachment tool paths. It's the symmetric counterpart of the file-write vulnerability you patched as CVE-2026-27825. The write direction was fixed; the read direction was left open. Reporter: Sean Valentin...

8.3CVSS6.1AI score0.00349EPSS
SaveExploits1References6
Vulnrichment
Vulnrichment
•added 2026/09/21 8:45 p.m.•12 views

CVE-2026-77521 MaxKB: Prompt-injectable agent can lead to command execution

MaxKB is an open-source AI assistant for enterprise. Prior to version 2.10.5-lts, assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend, which exposes an execute shell tool without excluding it and omits execute from interrupton, so human approval is not required...

10CVSS6.3AI score0.01049EPSS
SaveExploits0References3
Cvelist
Cvelist
•added 2026/09/21 8:45 p.m.•56 views

CVE-2026-77521 MaxKB: Prompt-injectable agent can lead to command execution

MaxKB is an open-source AI assistant for enterprise. Prior to version 2.10.5-lts, assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend, which exposes an execute shell tool without excluding it and omits execute from interrupton, so human approval is not required...

10CVSS0.01049EPSS
SaveExploits0References3
CVE
CVE
•added 2026/09/21 8:45 p.m.•40 views

CVE-2026-77521

MaxKB is an open-source enterprise AI assistant. Prior to 2.10.5-lts , assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend , which exposes an execute shell tool without excluding it and omits execute from interrupt_on, meaning no human approval is required before e...

10CVSS6.3AI score0.01049EPSS
SaveExploits0References3
OSV
OSV
•added 2026/09/21 8:45 p.m.•7 views

CVE-2026-77521 MaxKB: Prompt-injectable agent can lead to command execution

MaxKB is an open-source AI assistant for enterprise. Prior to version 2.10.5-lts, assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend, which exposes an execute shell tool without excluding it and omits execute from interrupton, so human approval is not required...

10CVSS6.1AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/09/21 6:10 p.m.•12 views

ironcurtain memory-mcp-server/v0.2.1

IronCurtain A secure runtime for autonomous AI agents, where security policy is derived from a human-readable constitution. When someone writes "secure," you should immediately be skeptical.What do we mean by secure? !WARNING Research Prototype. IronCurtain is an early-stage research project...

6.4AI score
SaveExploits0References3
Rows per page
Query Builder