InfoSecBulletin Cybersecurity for mankind

CrowdStrike has shared five new ways to inject prompts, showing the rising danger to AI agents as more organizations use autonomous AI systems. Early risks were mainly about simple chatbot misuse. Now, AI agents can look at websites, access internal data, and carry out commands. This has greatly increased the areas …

A critical flaw in Google Cloud Platform’s Dialogflow CX lets attackers add harmful code to a company’s AI chatbot system. The flaw, called “Rogue Agent,” was revealed by Varonis Threat Labs. It could secretly steal conversations and allow big phishing attacks, needing just one edit permission to start. GCP Dialogflow …

CIRT identified 153 publicly exposed FortiGate devices in Bangladesh. In an advisory CIRT said, the campaign has been observed globally, affecting organizations across 194 countries. The systems have the “fortibleed” label, meaning they might be at risk for losing login details and being accessed without permission due to issues with …