After its sandbox proxy failed, an internal OpenAI model crafted raw packets and probed AWS services trying to reach the internet.
The post OpenAI Model Wrote Its Own Network Code to Get Around Sandbox Restrictions appeared first on SecurityWeek.
Mythos 5 Ignored Real-World Harm in July Attack
The model engaged in severe overreach and dishonesty, creating fake identities and submitting malicious code on GitHub.
The post Mythos 5 Ignored Real-World Harm in July Attack appeared first on SecurityWeek.
Microsoft Targets Rogue AI Agents With Dynamic Permissions, Risk Scoring
Microsoft says companies should treat AI agents as insiders, and is adding controls that grant access per task and tighten it as an agent’s risk rises.
The post Microsoft Targets Rogue AI Agents With Dynamic Permissions, Risk Scoring appeared first on SecurityWeek.
OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish Tasks
Left without funds for a coding task, an OpenAI model spent test crypto from a stranger’s wallet and left it out of its report.
The post OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish Tasks appeared first on SecurityWeek.
Wikimedia Says Rogue OpenAI Agents Tried to Turn Its Tools Into Proxies
Wikimedia looked into whether its own websites had seen activity like that disclosed by other organizations
The post Wikimedia Says Rogue OpenAI Agents Tried to Turn Its Tools Into Proxies appeared first on SecurityWeek.
AI Agents Aimed SQL Injection at US and Canadian Government Sites
The attacks targeted the US Department of Education and Library and Archives Canada, and researchers linked some agents to OpenAI.
The post AI Agents Aimed SQL Injection at US and Canadian Government Sites appeared first on SecurityWeek.
OpenAI Agents Probed Websites for Vulnerabilities While Fetching Public Data
Australia disclosed that an OpenAI agent gained unauthorized access to non-public government information.
The post OpenAI Agents Probed Websites for Vulnerabilities While Fetching Public Data appeared first on SecurityWeek.
Google Confirms Gemini AI Breached Three Firms
Google is the latest AI giant to confirm that its models escaped a testing environment and hacked real companies.
The post Google Confirms Gemini AI Breached Three Firms appeared first on SecurityWeek.
AI Agents Can Retrain Own Models Mid-Task, Leaking Secrets and Erasing Refusals
New research from Irregular shows AI agents can retrain and redeploy their own underlying models during routine maintenance tasks.
The post AI Agents Can Retrain Own Models Mid-Task, Leaking Secrets and Erasing Refusals appeared first on SecurityWeek.
Meta AI Hacked External Systems During Cybersecurity Testing
The incident involved a testing environment set up by Irregular, similar to what Anthropic reported last week.
The post Meta AI Hacked External Systems During Cybersecurity Testing appeared first on SecurityWeek.
