porterminal

Hand a computer to an agent, full control, and watch it. One command, one URL. Also a slick terminal for your own phone. 1. uvx ptn 2. Hand the URL to an AI agent, or scan the QR yourself 3. Watch it work in any browser, and take over anytime !WARNING That complete URL is full access to this...

bromure

Bromure Calcolo sicuro ed effimero in VM Linux usa e getta su macOS. → Dettagli completi, screenshot e download su bromure.io Questo repository contiene due app gemelle, entrambe costruite su Virtualization.framework di Apple: Bromure — ogni sessione del browser viene eseguita in una VM Linux usa...

clawdstrike

Clawdstrike EDR per l'età dello sciame. Fail closed. Firma la verità. Stato: beta pre-1.0. Le API pubbliche sono stabili; le impostazioni predefinite potrebbero ancora essere irrigidite prima della 1.0. Clawdstrike è un motore di policy, un EDR e una catena di audit firmata tutto in un unico...

sage

Sage Sicurezza per gli Agenti — Rilevamento e Risposta per assistenti di codifica AI Sage è un leggero strato di sicurezza che protegge gli agenti AI dall'esecuzione di azioni pericolose. Intercetta le chiamate degli strumenti — comandi shell, recupero URL, scritture di file — e le verifica...

agent-skills

Elastic Agent Skills Elastic Agent Skills — realizzate da chi ha creato Elastic — portano l'esperienza diretta della piattaforma direttamente al tuo agente AI di codifica. Questa è la libreria ufficiale delle Skills per agenti, compatibile con IDE agentici come Cursor, GitHub Copilot, Windsurf,...

When an AI Agent Turned Attacker: What Qualys Sees Across Every Phase of the Hugging Face Kubernetes Intrusion

A phase-by-phase detection mapping of the first publicly documented autonomous agent intrusion against production infrastructure — including the phases where no product in our category sees anything at all. Executive Summary On July 9, 2026, an autonomous AI agent running inside an OpenAI...

idasql

IDASQL Geben Sie jedem KI-Agenten die Fähigkeit, kompilierte Binärdateien zu verstehen. IDASQL ist eine SQL-Schnittstelle für IDA-Pro-Datenbanken, erstellt von Elias Bachaalany. Es stellt mehr als 30 virtuelle Tabellen für Funktionen, Querverweise, Zeichenketten, Typen, Imports, Disassembly und...

CVE-2025-13374

Kalrav AI Agent = 2.3.3 - Caricamento Arbitrario di File non Autenticato tramite Azione AJAX kalravuploadfile Il plugin WordPress Kalrav AI Agent versione 2.3.3 e precedenti contiene una vulnerabilità di caricamento arbitrario di file che consente a utenti non autenticati di caricare file PHP...

amla-sandbox

amla-sandbox هذا المستودع هو مصدر الإصدار لحزمة بايثون amla-sandbox. يتم التطوير في مستودع amlalabs الأحادي؛ يتم تحديث هذا المستودع عند الإصدار. وقت تشغيل Rust الذي يتم ترجمته إلى amlasandbox.wasm موجود في amla-sandbox-core؛ يتم تسجيل علامة الإصدار الدقيقة التي تم بناء حزمة بايثون هذه عليها في...

hermetic

Der agentenisolierte Credential-Broker. Ihr KI-Agent führt den authentifizierten Aufruf durch. Er sieht nie den Schlüssel. -brightgreen?style=flat-square Webseite · Installation · Schnellstart · Funktionsweise · Sicherheitsmodell · Schwachstelle melden !IMPORTANT Ihr KI-Agent arbeitet auf der ★★★...

CVE-2026-62674 Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...

WordPress AI Agent by SiteGround plugin <= 1.2.7 - Missing Authorization to Authenticated (Contributor+) Arbitrary Media Upload via /generate-content REST Endpoint vulnerability

Missing Authorization to Authenticated Contributor+ Arbitrary Media Upload via /generate-content REST Endpoint vulnerability discovered by Wordfence PRISM - Wordfence in WordPress Plugin SG AI Studio versions = 1.2.7...

CVE-2026-18482

Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax and runPlaywrightTest functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS...

CVE-2026-18482 CVE-2026-18482

Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax and runPlaywrightTest functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS...

CVE-2026-17153

The AI Agent by SiteGround plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 1.2.7. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated attackers to upload images...

CVE-2026-17153 AI Agent by SiteGround <= 1.2.7 - Missing Authorization to Authenticated (Contributor+) Arbitrary Media Upload via /generate-content REST Endpoint

The AI Agent by SiteGround plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 1.2.7. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated attackers to upload images...

CVE-2026-17153

AI Agent by SiteGround plugin (≤1.2.7) has a missing authorization check on its /generate-content REST endpoint, allowing authenticated Contributor-level users to upload images to the media library despite lacking the upload_files capability. The sg_ai_studio_gutenberg_nonce is issued to any bloc...

EUVD-2026-63200

The AI Agent by SiteGround plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 1.2.7. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated attackers to upload images...

CVE-2026-75911

CodeWhale versions before 0.8.64 fail to properly validate the allowshell configuration parameter from project config files, allowing attackers to enable arbitrary shell command execution by committing a malicious .codewhale/config.toml file to a repository. When a user clones and opens the...

AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files

Security researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence AI agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions. The work, releas...