OneAlert

OneAlert AI Security OS Ciberdefensa autónoma de código abierto para redes industriales Agentes de IA que detectan, investigan, buscan y responden a amenazas en tu infraestructura OT/ICS — con puertas de aprobación humana y registros de auditoría completos. Demo Setup · Características · Inicio...

MakerChecker

🛡️ MakerChecker La capa de seguridad de código abierto para agentes de IA. Aplicación por defecto de denegación, aprobaciones humanas y un rastro de auditoría firmado criptográficamente — para que tu agente ejecute solo lo que se le ha concedido y no pueda probadamente aprobar su propio trabajo...

skillscript

Automatización segura y reutilizable creada por agentes. skillscript.ai • documentación Resumen — npm install -g skillscript-runtime && skillfile init && skillfile dashboard. Ver Inicio rápido. ¿Qué es Skillscript? Skillscript surgió de preguntarse: ¿qué aspecto tendría un Makefile si en lugar de...

PT-2026-55225

Name of the Vulnerable Software and Affected Versions FlowDrop versions 0.0.0 through 1.6.0 Description A missing authorization issue allows forceful browsing. The module, which enables testing and running AI-driven workflows via a chat interface, fails to sufficiently re-evaluate human-in-the-lo...

cruxss-bb-agent

CRUXSS Bug Bounty Agent A semi-autonomous bug bounty hunting...

AEGIS: No Tool Call Left Unchecked -- a Pre-Execution Firewall and Audit Layer for AI Agents

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer with no framework-agnostic control point in between...

Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)

Impact MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare + execute without semantic restrictions. This is consistent with the name “write tool”, but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause...

CVE-2025-64108

Cursor is a code editor built for programming with AI. In versions 1.7.44 and below, various NTFS path quirks allow a prompt injection attacker to circumvent sensitive file protections and overwrite files which Cursor requires human approval to overwrite. Modification of some of the protected fil...

CVE-2025-64108

Cursor is a code editor built for programming with AI. In versions 1.7.44 and below, various NTFS path quirks allow a prompt injection attacker to circumvent sensitive file protections and overwrite files which Cursor requires human approval to overwrite. Modification of some of the protected fil...