‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets
Deceptive prompts lure AI agents into decoys and dead ends, cutting attack success by up to 91% in tests and raising the cost of a successful attack 23-fold.
Actualizado hace 1 min
Noticias de ciberseguridad
Alertas de vulnerabilidades explotadas, exploits y pruebas de concepto, malware, ransomware e incidentes con contenido técnico, de los medios de ciberseguridad en castellano. Se actualiza solo durante todo el día.
12 notas en castellano e inglés. Quitar filtros
VulnerabilidadesExploits y PoC
High-Severity Flaws Exploited in Three Days as Ransomware Dominates Q3: Rapid7
Rapid7’s Q3 analysis finds high-severity flaws exploited within three days on average, while AI appeared in just 8% of tracked incidents.
IA y seguridadHerramientas e investigación
Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security
Asymptote Labs raises $5.5M seed led by Tower Research Ventures to commercialize its Beacon AI agent runtime security platform.
Memory Bugs Account for Most of Chrome’s 353 New Security Fixes
The update fixes 353 flaws, including 163 memory corruption and 125 use-after-free vulnerabilities.
Ciberseguridad
OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor
In two internal incidents, agents read routine coding instructions as permission to weaken monitoring, and one gave a false answer about it.
Ciberseguridad
Browsers Block eMudhra Intermediate CAs Over Recoverable Private Keys
The private keys associated with eight certificates were compromised, and root programs and trust stores are blocking them.
China Defends DeepSeek After US Ban of Its AI From Government Systems
The DHS said agencies should remove DeepSeek products as well as third-party products and services developed using DeepSeek from their IT systems.
Chinese AI Model Writes More Hackable Code When Told It’s for US Contractor
Tasked with writing an application for a US defense contractor, the model made the code 19% more likely to be hackable.
VulnerabilidadesExploits y PoC
PHP2Shell: Mass Exploitation Looms for Leaked Critical PHP Flaws
Tracked as CVE-2026-109618 and CVE-2026-109619, the bugs could potentially lead to unauthenticated remote code execution.
MalwareHerramientas e investigación
Hijacked Developer Account Used to Plant Stealer in OVHcloud CLI
Researchers say the developer’s account was compromised in March with a GlassWorm-linked loader.
Infraestructura críticaHerramientas e investigación
Accenture, Dragos, SANS Launch $10M Initiative to Defend Small US Utilities
The first phase will cover up to 500 utilities, which will get free security tools, equipment, deployment help and training.
US Agencies Detail Incident Response Practices for Rogue AI Agents
NIST, CISA and NSA share ten voluntary practices for preparing for, detecting, responding to, recovering from, and reporting rogue AI agent incidents.