El blog chileno oficial de la Seguridad en Inteligencia Artificial
Lo que pasa en seguridad, filtrado para quien gobierna IA
Dos capas: nuestros análisis sobre gobernanza y seguridad de inteligencia artificial, y un radar que revisa automáticamente las fuentes de referencia del sector y clasifica cada titular por categoría y severidad.
Análisis SeguridadIA
Escritos por nuestro equipo, pensados para decidir: qué controlar primero, con qué evidencia y en qué orden. Los 33 están ordenados por área en Investigación.
Prompt injection: por qué tus guardrails no bastan
La inyección de prompts no es un bug que se parchea, es consecuencia de cómo funciona un modelo de lenguaje. Qué controlar cuando el filtro de entrada falla.
Leer análisisAnatomía de un ataque a un sistema de IA
Dónde empieza y dónde termina la superficie de ataque de una aplicación con modelos: datos, modelo, contexto, herramientas y personas.
Leer análisisEl OWASP Top 10 para LLM explicado sin jerga
Los diez riesgos del estándar traducidos a decisiones concretas de arquitectura, con el control que corresponde a cada uno.
Leer análisisMITRE ATLAS: cómo leer las tácticas de ataque contra IA
Qué es ATLAS, en qué se diferencia de ATT&CK y cómo usarlo para ordenar tu propio modelado de amenazas.
Leer análisisShadow AI: cómo inventariar en dos semanas lo que ya se está usando
Un plan de diez días para levantar el uso real de IA en tu organización, clasificarlo por sensibilidad del dato y decidir qué formalizar, acotar o sustituir.
Leer análisisEnvenenamiento de datos: el ataque que ocurre antes del despliegue
Cómo se contamina un conjunto de entrenamiento o una base vectorial, por qué es difícil de detectar y qué controles aplican en la práctica.
Leer análisisExtracción de modelos y fuga de datos de entrenamiento
Qué puede reconstruir un atacante consultando tu modelo, qué revela sin querer y cómo limitar la exposición sin romper el producto.
Leer análisisAgentes con herramientas: el modelo de permisos que casi nadie diseña
Por qué heredar los permisos del usuario es el error más común en agentes corporativos y cómo se ve un diseño de autorización correcto.
Leer análisisSeis controles de seguridad de IA que puedes implementar este trimestre
Los marcos describen el destino pero no el orden del camino. Seis controles concretos, priorizados por reducción de riesgo sobre esfuerzo, y cómo repartirlos en 90 días.
Leer análisisRadar de amenazas
Titulares recogidos de los feeds públicos de cada medio y clasificados automáticamente. Cada entrada enlaza a la fuente original: aquí solo verás el titular y un extracto breve.
-
Incident Report: unsanctioned agent behaviour during cyber testing
Incident Report: unsanctioned agent behaviour during cyber testing It happened again. This time it was the UK government's AI Security Institute who accidentally attacked other companies while running an evaluation with models with the…
Simon Willison Seguridad IA simonwillison.net -
AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking
Attackers can take control of agents through malicious instructions hidden in content supplied to AI browsers, and there's no simple fix for the threat.
Dark Reading Seguridad IA darkreading.com -
Ransom Cartel ransomware creator sentenced to 16 years in prison
Maksim Silnikau, the creator and administrator of the Ransom Cartel ransomware operation, was sentenced to 16 years in prison for his role in ransomware attacks against at least 18 companies worldwide. [...]
BleepingComputer Amenazas bleepingcomputer.com -
No Perfect Fix for AI Browser Prompt Injection Flaws
AI browsers from top vendors remain vulnerable to prompt injection attacks despite multiple security guardrails, according to new research.
Dark Reading Seguridad IA darkreading.com -
Canadian pleads guilty to Snowflake cloud data-theft attacks
A Canadian man pleaded guilty today to his role in accessing company accounts at cloud storage provider Snowflake and stealing data from at least 165 organizations in a scheme to extort millions of dollars from victims. [...]
BleepingComputer Infraestructura bleepingcomputer.com -
Prompt injection isn't the bug, AI agent frameworks are
Check Point researchers tried to break the frameworks enterprises use to build AI apps. Now they're telling Black Hat attendees what they found
The Register · Security Seguridad IA theregister.com -
Chinese telcos maintain deep US presence despite Salt Typhoon links, House committee says
Three Chinese telecommunications giants continue to have footholds in the U.S. internet ecosystem despite their alleged role in previous Chinese hacking campaigns, a House committee report concluded.
The Record Amenazas therecord.media -
Hackers run khunt post-exploitation toolkit from Oracle database
Hackers exploited a SQL injection vulnerability to install a post-exploitation toolkit directly inside an Oracle database that was used to breach a corporate network. [...]
BleepingComputer Vulnerabilidades bleepingcomputer.com -
CSS: The Hidden Threat Lurking in Your Inbox
CSS was once just about design. Now researchers warn it's powerful enough to exfiltrate data from webmail — and some vendors aren't prepared.
Dark Reading General darkreading.com -
One-shotting a Raccoon Heist game using Claude Fable 5
Back in 2022 I tweeted screenshots of a game concept generated by GPT-3 and some concept "art" created using DALL-E. Today, on the fourth anniversary of that tweet, I decided to see if Claude Fable 5 (running in Claude Code for web) could…
Simon Willison Seguridad IA simonwillison.net -
How a $50,000 Exploit Chain Turned Bixby Against Samsung Phones
The chain involved the exploitation of several vulnerabilities in the Samsung Members and Samsung Account applications. The post How a $50,000 Exploit Chain Turned Bixby Against Samsung Phones appeared first on SecurityWeek.
SecurityWeek Vulnerabilidades securityweek.com -
15 TP-Link Bugs Expose Risks in Zero-Trust Provisioning
Researchers are calling attention to the risks inherent in automated network device provisioning, using a world-leading device manufacturer as a case study.
Dark Reading General darkreading.com -
Over 250 ClickFix Domains Use Browser Fingerprinting to Hide macOS Malware Lures
A macOS ClickFix operation spanning more than 250 front-end domains now fingerprints visitors before deciding whether to show them a malware lure, a change Microsoft Threat Intelligence tracked on infrastructure it had been watching for…
The Hacker News Amenazas thehackernews.com -
OpenAI Disrupts Poipet Scam Network Using ChatGPT Across Multiple Fraud Schemes
OpenAI said it disrupted a Cambodia-based scam operation that used its generative artificial intelligence (AI) chatbot ChatGPT to facilitate a wide range of investment, romance, gambling, and law enforcement impersonation schemes. To that…
The Hacker News Seguridad IA thehackernews.com -
Flaws in Google APK for Python Unlock Agent-to-Agent Attack
Google has fixed the issues, which exploited a trust boundary between two AI agents with different privilege levels to trigger automation that could compromise the supply chain.
Dark Reading Seguridad IA darkreading.com -
COLDCARD security audit phishing attack installs remote access tool
A phishing campaign is exploiting fears surrounding the recently disclosed COLDCARD wallet vulnerability and suspected $88.6 million Bitcoin theft to trick users into installing ScreenConnect remote access software. [...]
BleepingComputer Vulnerabilidades bleepingcomputer.com -
IBM's agentic AI platform is under active attack - patch now
A critical Langflow flaw allowing RCE on default deployments is being exploited, says the CISA
The Register · Security Seguridad IA theregister.com -
Microsoft named a Leader in the KuppingerCole Leadership Compass for Cloud Native Application Protection Platforms (CNAPP)
Learn why KuppingerCole named Microsoft a Leader in its Leadership Compass: Cloud Native Application Protection Platforms report. The post Microsoft named a Leader in the KuppingerCole Leadership Compass for Cloud Native Application…
Microsoft Security Blog Infraestructura microsoft.com -
CISA warns of hackers exploiting Langflow, N-central, Apache Tomcat flaws
The U.S. Cybersecurity and Infrastructure Security Agency is giving federal agencies three days to mitigate vulnerabilities in IBM Langflow, N-central, and Apache Tomcat, all actively exploited. [...]
BleepingComputer Vulnerabilidades bleepingcomputer.com -
From open lures to cloaked gates: How a macOS ClickFix campaign learned to hide
A macOS ClickFix campaign shifted tactics from openly serving infostealer lures to hiding them behind a browser-fingerprinting gate. The change makes malicious infrastructure harder to detect while giving defenders new hunting…
Microsoft Security Blog Amenazas microsoft.com -
Poison Claude Sells Discounted Claude Access While Its Operator Sees Every Customer Prompt
Cybersecurity researchers have discovered more than half-a-dozen services advertisements for illegal access to artificial intelligence (AI) models on underground cybercrime forums and messaging platforms. One such service, Poison Claude…
The Hacker News Seguridad IA thehackernews.com -
Paperclip AI Flaws Let Attackers Run Host Commands via Malicious Agent Imports
Two security flaws in Paperclip could let attackers execute commands on a network server or a developer's computer. Paperclip is an open-source control plane for teams of artificial intelligence (AI) agents, and both paths rely on…
The Hacker News Seguridad IA thehackernews.com -
Google Blogger locks hundreds of blogs in malware false positive
Google has locked hundreds of Blogger websites after a false positive claimed they violated its "Malware and Similar Malicious Content" policy, with some sites deleted from the platform. [...]
BleepingComputer Amenazas bleepingcomputer.com -
Black Hat USA 2026 – Summary of Vendor Announcements (Part 3)
Many companies are showcasing their products and services this week at the 2026 edition of the Black Hat conference in Las Vegas. The post Black Hat USA 2026 – Summary of Vendor Announcements (Part 3) appeared first on SecurityWeek.
SecurityWeek General securityweek.com -
Veeam, Terraform MCP, Django Patch Critical Flaws, Led by CVSS 10.0 Cross-Tenant Bug
HashiCorp, Veeam, and the Django Software Foundation have patched 11 vulnerabilities across Terraform MCP Server, Veeam Service Provider Console, and Django. The three most serious: An unauthenticated flaw in Veeam's console that hands…
The Hacker News Seguridad IA thehackernews.com
¿Y esto qué significa para ti?
Traducimos el ruido en un plan de control
Leer titulares no reduce el riesgo. Armemos el diagnóstico de tu exposición real y una hoja de ruta de 90 días con responsables y evidencia.