Latest cybersecurity reporting from selected sources.

Researchers who found the flaws scored beer money bounties and warn the problem is probably pervasive Exclusive Security researchers hijacked three popular AI agents that integrate with GitHub Actions by using a new type of prompt injection attack to steal API keys and access tokens, and the vendors who run agents didn’t disclose the problem.…

Probably not an isolated incident only as researchers have already found 2,863 live API keys exposed A developer says their company is on the hook for more than $82,000 in unauthorized charges after a stolen Google Gemini API key racked massive usage costs up in just 48 hours.…

New research has found that Google Cloud API keys, typically designated as project identifiers for billing purposes, could be abused to authenticate to sensitive Gemini endpoints and access private data

Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in which private-sector firms and researchers use legitimate API access to systematically probe models and replicate their logic and reasoning. [...]

Cybersecurity researchers have disclosed details of a malicious Google Chrome extension that's capable of stealing API keys associated with MEXC, a centralized cryptocurrency exchange (CEX) available in over 170 countries, while masquerading as a tool to automate trading on the platform

Cybersecurity researchers have disclosed details of a new fully-featured Windows backdoor called NANOREMOTE that uses the Google Drive API for command-and-control (C2) purposes

Google Gemini's one of the most powerful features is Deep Research, but up until now, it has been strictly limited to the Gemini interface. This could change soon. [...]

Cybersecurity researchers have flagged several popular Google Chrome extensions that have been found to transmit data in HTTP and hard-code secrets in their code, exposing users to privacy and security risks

Google's Gemini large language model (LLM) is susceptible to security threats that could cause it to divulge system prompts, generate harmful content, and carry out indirect injection attacks

Infosec folk aren’t thrilled that if you poke APIs enough, you learn AI's secrets Boffins have managed to pry open closed AI services from OpenAI and Google with an attack that recovers an otherwise hidden portion of transformer models.…

Researchers at Lasso found 1,500+ tokens in total that gave them varying levels of access to LLM repositories at Google, Microsoft, VMware, and some 720 other organizations.

With more than 1,500 tokens exposed, research highlights importance of securing supply chains in AI and ML The API tokens of tech giants Meta, Microsoft, Google, VMware, and more have been found exposed on Hugging Face, opening them up to potential supply chain attacks. …

Cybersecurity researchers have detailed a "severe design flaw" in Google Workspace's domain-wide delegation (DWD) feature that could be exploited by threat actors to facilitate privilege escalation and obtain unauthorized access to Workspace APIs without super admin privileges

The finding exposes the danger of older, unpatched bugs, which plague at least 4.5 million devices.