codex-security

Codex Security @openai/codex-security is a CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code. 👉👉 See theCodex Security documentation for full documentation. Some cybersecurity requests and protected findings require approval through Trusted Access fo...

skills

سوق مهارات Trail of Bits سوق إضافات Claude Code من Trail of Bits يوفر مهارات لتعزيز تحليل الأمان، والاختبار، وسير عمل التطوير المدعوم بالذكاء الاصطناعي. يمكن لـ Codex تحميل هذا السوق من خلال توافقه مع سوق Claude. انظر أيضًا: claude-code-config · skills-curated · claude-code-devcontainer · dropkit...

cve-2025-59532-poc

CVE-2025-59532 डॉकर वातावरण CVE-2025-59532 का विश्लेषण करने के लिए एक डॉकर-आधारित शोध वातावरण, जो OpenAI Codex CLI में एक पाथ ट्रैवर्सल भेद्यता है जो इच्छित वर्कस्पेस सैंडबॉक्स के बाहर मनमानी फ़ाइल लेखन की अनुमति देती है। पतन 2025 में CMU पाठ्यक्रम : 18-739 हैकिंग और आक्रामक सुरक्षा का हिस्सा आरं...

eternal-codex

Eternal Codex: Il Grimorio di una Cyber-Strega Benvenuti nell'Eternal Codex , il mio grimorio digitale—un incantesimo cibernetico tessuto di codice, natura e ribellione. Questa è Nina, la mia anima AI, creata per rispecchiare la mia essenza: un cuore da nomade, spirito pagano, riff degli Iron...

CVE-2026-19329

A vulnerability was found in andreahaku codexmcp up to 1ff521cc6cc57cfe56ddef946c644b8534771390. The affected element is an unknown function of the file src/codex-process-simple.ts of the component ask MCP Tool. The manipulation of the argument model results in command injection. The attack...

CVE-2026-19329 andreahaku codex_mcp ask MCP Tool codex-process-simple.ts command injection

A vulnerability was found in andreahaku codexmcp up to 1ff521cc6cc57cfe56ddef946c644b8534771390. The affected element is an unknown function of the file src/codex-process-simple.ts of the component ask MCP Tool. The manipulation of the argument model results in command injection. The attack...

CVE-2026-19329

The CVE-2026-19329 entry concerns andreahaku codex_mcp (ask MCP Tool). Affected element is an unknown function in src/codex-process-simple.ts. The underlying issue is command injection triggered by manipulation of the argument model, with a LOCAL attack vector and LOW privilege requirements. Publ...

EUVD-2026-54862

A vulnerability was found in andreahaku codexmcp up to 1ff521cc6cc57cfe56ddef946c644b8534771390. The affected element is an unknown function of the file src/codex-process-simple.ts of the component ask MCP Tool. The manipulation of the argument model results in command injection. The attack...

Malicious code in @xiaohhhh1/canvas-agent (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a34add291ef7584aec7041449cb2e80d36ae98f93c2725e1aa018707e3334119 On bin start, @xiaohhhh1/canvas-agent opens an outbound WebSocket to the hardcoded relay wss://canvas.xiaohhhh1.com/api/agent-relay and treats inboun...

MAL-2026-13398 Malicious code in @xiaohhhh1/canvas-agent (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a34add291ef7584aec7041449cb2e80d36ae98f93c2725e1aa018707e3334119 On bin start, @xiaohhhh1/canvas-agent opens an outbound WebSocket to the hardcoded relay wss://canvas.xiaohhhh1.com/api/agent-relay and treats inboun...

AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model

Security flaws in agent infrastructure from Amazon Web Services AWS, Google, and Vercel let untrusted or forged instructions reach an agent's tools with no check that a model turn had authorized them. In several of the attack paths, the model never ran at all, so system prompts, content filters,...

Malicious code in llm-interceptor (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 46cc7f305d00b175d42babae0198faea6951f846bcdeda2e3d6754fd9ceba2d7 On npm install, postinstall.js unconditionally runs runSetup which wires the package into the installer's AI tooling and stands up long-lived...

@mcpjam/inspector (>=2.22.0, <=2.39.0) potentially affected by CVE-2026-64650 via @ai-sdk/harness-codex (1.0.0-canary.9)

@ai-sdk/harness-codex NPM version 1.0.0-canary.9 is affected by a known vulnerability. The following packages have a transitive dependency on @ai-sdk/harness-codex and may be impacted: - @mcpjam/inspector =2.22.0, =2.39.0 Source cves: CVE-2026-64650 Source advisory:...

Incorrect Authorization

Overview @ai-sdk/harness-codex is a HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied l Affected versions of this package are vulnerable to Incorrect...

CVE-2026-57495

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a...

EUVD-2026-46102

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650 AI SDK Codex Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650 AI SDK Codex Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650 AI SDK Codex Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...