More results...
Today at WebexOne in San Diego, you will see an incredible convergence of vision, innovation, and community. This event is not just a showcase—it’s a testament to how Cisco is reimagining the future of work and building solutions for the AI era.
Researchers found more methods for tricking an AI assistant into aiding sensitive data theft.
The post Google Patches Gemini AI Hacks Involving Poisoned Logs, Search Results appeared first on SecurityWeek.
Microsoft Threat Intelligence detected a new AI-powered phishing campaign using LLMs to hide malicious code inside SVG files disguised as business dashboards.
Trend Micro reveals that RepairIt “contradicted its privacy policy by collecting, storing, and, due to weak Development, Security, and Operations practices, inadvertently leaking private user data.”
The post Security Breaches Found in AI-Powered Repair…
India’s Border Security Force (BSF), in collaboration with the Indian Space Research Organisation (ISRO), is developing radar-mounted drones to enhance surveillance along the nation’s western and eastern frontiers. This initiative represents a strategic modernization in border management, combining aerial mobility with advanced sensing technologies.What are Radar-Mounted Drones?Radar-mounted
Notion just released version 3.0, complete with AI agents. Because the system contains Simon Willson’s lethal trifecta, it’s vulnerable to data theft though prompt injection.
First, the trifecta:
The lethal trifecta of capabilities is:
- Access to your private data—one of the most common purposes of tools in the first place!
- Exposure to untrusted content—any mechanism by which text (or images) controlled by a malicious attacker could become available to your LLM
- The ability to externally communicate in a way that could be used to steal your data (I often call this “exfiltration” but I’m not confident that term is widely understood.)…
Researchers disclosed a critical flaw, named ForcedLeak, in Salesforce Agentforce that enables indirect prompt injection, risking CRM data exposure. Noma Labs researchers discovered a critical vulnerability, named ForcedLeak (CVSS 9.4), in Salesforce Agentforce that could be exploited by attackers to exfiltrate sensitive CRM data through an indirect prompt injection attack. The vulnerability only impacts organizations […]
Researchers disclosed a critical flaw, named ForcedLeak, in Salesforce Agentforce that enables indirect prompt injection, risking CRM data exposure. Noma Labs researchers discovered a critical vulnerability, named ForcedLeak (CVSS 9.4), in Salesforce Agentforce that could be exploited by attackers to exfiltrate sensitive CRM data through an indirect prompt injection attack. The vulnerability only impacts organizations […]
During Proofpoint Protect 2025, company leaders detailed how AI is being used in phishing trends and in cyber-defense tactics.
The post Proofpoint Exec: ‘Phishing is the Leading Cause of Breaches Globally’ appeared first on eSecurity Planet.
Proofpoint expands human-centric security to protect AI agents, safeguarding collaboration points and shared data in the agentic workspace.
The post Proofpoint’s New Agentic AI Cybersecurity Solutions Address 4 Key Challenges appeared first on eSecurity Planet.