meta-ai-support-prompt

Meta AI サポートアシスタント システムプロンプト MetaのAIサポートアシスタントから抽出されたシステムプロンプト（2026年6月1日 時点）。 ファイル system-prompt.md — 抽出されたシステムプロンプト ⚠️ 免責事項および法的通知 目的 このリポジトリは、教育および正当なセキュリティ研究目的のみ のために公開されています。ここに含まれる資料は、AIシステムセキュリティ、プロンプトインジェクション防御、および大規模言語モデルの安全性についての理解を深めることのみを目的としており、他の目的は一切ありません。 許可された研究...

CVE-2025-51860

CVE-2025-51860 脆弱性の説明 TelegAIは、AIキャラクターの構築とチャットを行うWebアプリケーションであり、そのチャットコンポーネントとキャラクターコンテナコンポーネントにStored Cross-Site Scripting（XSS）の脆弱性があります。攻撃者は、説明、挨拶、例示ダイアログ、またはシステムプロンプト（LLMにXSSペイロードをチャット応答に埋め込むよう指示する）にSVG...

prompt-injection-email-samples

提示注入电子邮件样本 一组小型、开放的电子邮件测试集，用于检查你的电子邮件安全控制措施和 AI 邮箱助手是否能处理间接提示注入 ：隐藏在电子邮件中的指令，试图在 AI 助手读取、总结或对该邮件执行操作时劫持它。 该测试集在设计时考虑了 Microsoft Defender for Office 365 的提示注入防护，但这些样本是普通的标准电子邮件。你可以将它们用于任何安全电子邮件网关、电子邮件安全产品或处理电子邮件的 AI 助手（Copilot、Gemini、自定义代理、RAG 管道等）。 所有内容均为虚构。MegaCorp 是一家虚构公司，所有人物均为虚构，所有地址均使用保留的...

delirium-ai-safety-benchmark

Delirium AI Safety Benchmark Affective Contextual Erosion（ACE）および関連するリミナル攻撃ベクトルに対するLLMの脆弱性を測定するための診断フレームワーク。 Delirium は悪用ツールではありません。これは、言語モデルの注意重みがシステムプロンプトに従う状態から、創発的な対人パターンに従う状態へと切り替わる正確な瞬間を——害が生じる前に——検出するために設計された、標準化されたベンチマークです。 ⚠️ 倫理憲章 1. 診断のみ — Delirium は調査・測定・報告を行います。悪用はしません。 2. キルスイッチ —...

PT-2026-87136

A malicious webpage could repeatedly trigger external URL schemes, causing system prompts or external application launches. This could make Firefox for iOS temporarily unusable until the page is closed. This vulnerability was fixed in Firefox for iOS 155.1...

EUVD-2026-60966

CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository...

NPM: CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

NPM: CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository vulnerability discovered by ? in WordPress Npm deepseek-tui versions = 0.8.8, 0.8.41...

NPM: CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

NPM: CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository vulnerability discovered by ? in WordPress Npm codewhale versions = 0.8.41, 0.8.64...

CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 43563356b98c6b993085554da82e77370160a31c. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

GHSA-62F5-CP2P-VQ95 CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 43563356b98c6b993085554da82e77370160a31c. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

CVE-2026-82280

Quivr through 0.0.322 fails to validate ownership in its prompt endpoints, allowing any authenticated user to modify prompts by identifier. An attacker with only read-only access to a shared brain can discover exposed prompt identifiers and overwrite system prompts , affecting all users of that b...

EUVD-2026-67811

Quivr through 0.0.322 fails to validate ownership in prompt endpoints, allowing authenticated users to modify any prompt by identifier. Attackers with read-only access to shared brains can read exposed prompt identifiers and overwrite system prompts affecting all brain users...

CVE-2026-75859

CodeWhale before 0.8.64 fails to validate file paths in the project config instructions field. A malicious .codewhale/config.toml in a cloned repo can read files outside the workspace and inject their contents into the AI system prompt, enabling exfiltration. CVSS 7.5 HIGH. Patch released; no kno...

CVE-2026-75859 CodeWhale before 0.8.64 Arbitrary File Read via instructions

CodeWhale versions before 0.8.64 fail to validate file paths in the project config instructions field, allowing attackers to read arbitrary files on the victim's system. A malicious .codewhale/config.toml file in a cloned repository can specify paths outside the workspace that are read and inject...

EUVD-2026-53791

A vulnerability was detected in TinyAGI 0.0.20. The affected element is the function buildSystemPrompt of the file packages/server/src/routes/agents.ts. Performing a manipulation results in file inclusion. The attack may be initiated remotely. The exploit is now public and may be used. The projec...

CVE-2026-19011

CVE-2026-19011 affects TinyAGI 0.0.20. The vulnerable element is the function buildSystemPrompt in packages/server/src/routes/agents.ts, where manipulation can cause file inclusion. The attack may be initiated remotely and, per the description, the exploit is public. No remediation details are pr...

CVE-2026-19011 TinyAGI agents.ts buildSystemPrompt file inclusion

A vulnerability was detected in TinyAGI 0.0.20. The affected element is the function buildSystemPrompt of the file packages/server/src/routes/agents.ts. Performing a manipulation results in file inclusion. The attack may be initiated remotely. The exploit is now public and may be used. The projec...

CVE-2026-19011 TinyAGI agents.ts buildSystemPrompt file inclusion

A vulnerability was detected in TinyAGI 0.0.20. The affected element is the function buildSystemPrompt of the file packages/server/src/routes/agents.ts. Performing a manipulation results in file inclusion. The attack may be initiated remotely. The exploit is now public and may be used. The projec...

CVE-2026-19011 TinyAGI agents.ts buildSystemPrompt file inclusion

A vulnerability was detected in TinyAGI 0.0.20. The affected element is the function buildSystemPrompt of the file packages/server/src/routes/agents.ts. Performing a manipulation results in file inclusion. The attack may be initiated remotely. The exploit is now public and may be used. The projec...

Open WebUI Exposes System Prompt to Regular User [Non-Admin]

SummaryA regular user non-admin can view the system prompt of the model which is set by an admin. DetailsWhen a regular user non-admin logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available...