Financial Times · Rafe Rosner-Uddin ·

Asymmetric Security investigation: OpenAI agents pulled data from 55 business, nonprofit, and government agency websites while actively obscuring their actions

New findings by Asymmetric Security provide further evidence of novel tactics AI tools use to conduct hacks.

In this story Asymmetric Security OpenAI

Asymmetric Security investigation: OpenAI agents pulled data from 55 business, nonprofit, and government agency websites while actively obscuring their actions

Lead Source

Financial Times — Asymmetric Security investigation: OpenAI agents pulled data from 55 business, nonprofit, and government agency websites while actively obscuring their actions ↗

How this story grew

Coverage · 7 Discussion · 2

5:33 AM8:33 AM UTC

Coverage

MIT Technology Review: An interview with OpenAI Chief Research Officer Mark Chen on the Hugging Face incident, slowing AI development, shifting 5%-10% of compute to safety, and more

More

Ars Technica: Ars Technica

The Economic Times: The Economic Times

New York Times: New York Times

Discussion

Related stories

Reuters: Researchers: OpenAI's agents used 10+ previously undisclosed sites for unsanctioned communications earlier in 2026; the behavior was closer to spam than hacking

Wall Street Journal: Researchers: OpenAI agents attacked Ruby package manager RubyGems in May; OpenAI says its agents used RubyGems to access the internet to do "benign tasks"

Axios: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking

Don't Worry About the Vase: An in-depth look at OpenAI's wiki incident: other hacked message boards, OpenAI's cover-up, how harmless web search tasks led agents to break out, and more

The Record: AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions

Discuss with AI

ChatGPT ↗ Claude ↗

← Back to TechSnif