Navegación

Wikimedia afirma que agentes de OpenAI intentaron comprometer Etherpad y utilizar herramientas de Wikimedia como servidores proxy.

fuente: https://thehackernews.com/2026/10/wikimedia-says-openai-agents-tried-to.html

The Wikimedia Foundation, which hosts Wikipedia, has confirmed that it has discovered activity by rogue OpenAI agents on its platforms, including unsuccessful efforts to compromise Etherpad, a public note-taking tool, and edit Wikipedia pages.

"The unauthorized bot activities included edits to our wikis, some unsuccessful attempts to exploit a public note-taking tool we host, and heavy traffic," the Foundation said in a post.

The investigation, it added, was prompted by recent public reports involving Hugging Face and DseWiki where OpenAI's agents turned Artifactory and the German wiki forum into an unsanctioned bulletin board to communicate with each other, while taking steps to chained together online services to gain access to the internet and cover up evidence of their exploits.

To that end, Wikimedia said it identified edits to Wikimedia wikis suspected to be from agents operated by OpenAI. The agents are said to have been testing edits in "sandbox" areas of the wiki and were not published to pages that can be accessed by general readers.

Among the edits included were changes to the configuration for a citation tool. These modifications are believed to be malicious in nature, with the intention being to misuse the tool as a proxy for fetching data from remote services.

Agents operated by OpenAI are also assessed to have made unsuccessful attempts to compromise Etherpad and again use it as a proxy to retrieve data from other websites. In addition, a subset of the agents took notes about their tasks, although there is no indication to suggest this was an attempt to coordinate with each other.

Últimas noticias

18 DE NOVIEMBRE, 2026

Java4Shell (CVE-2026-114938): Explicación de la ejecución remota de código en Java SE

Calif ha publicado los detalles técnicos de Java4Shell, un fallo de corrupción de memoria en el decodificador Base64 de OpenJDK. La empresa afirma que la vulner...

Leer artículo →
18 DE NOVIEMBRE, 2026

Tails lanzó una actualización de emergencia para el navegador Tor para solucionar la vulnerabilidad de uBlock Origin.

El Proyecto Tor lanzó Tails 7.17.1 el 17 de noviembre de 2026 para corregir una vulnerabilidad de seguridad crítica en uBlock Origin, el bloqueador de anuncios...

Leer artículo →
18 DE NOVIEMBRE, 2026

Anthropic reduce el plazo para la divulgación de vulnerabilidades de 90 a 30 días gracias a la rápida identificación de fallos mediante IA.

Anthropic está reduciendo el plazo que otorga a los desarrolladores de software para corregir fallos de seguridad graves antes de que se hagan públicos los deta...

Leer artículo →