Vulnerability Research | Breaking Cybersecurity News | The Hacker News

Cybersecurity researchers have disclosed details of a vulnerability in OpenAI ChatGPT that leverages the artificial intelligence (AI) assistant's implicit trust in Markdown links and images to trigger prompt injections and open the door to phishing attacks. The technique has been codenamed ChatGPhish by Permiso Security. "The chatgpt.com response renderer trusts Markdown links and Markdown image URLs that originated from a third-party page the assistant has just summarized. It auto-fetches those images and surfaces those links as live, clickable elements inside the trusted assistant UI," security researcher Andi Ahmeti said in a report shared with The Hacker News. In a hypothetical attack scenario, a bad actor can append a small payload to any web page that the victim later prompts ChatGPT to summarize, causing it to leak their IP, User-Agent, and Referer details when attacker-hosted images embedded in the page are automatically fetched when the answer is rendered...

While Gartner does not have a dedicated Magic Quadrant for Bug Bounties or Crowd Security Testing yet, Gartner Peer Insights already lists 24 vendors in the "Application Crowdtesting Services" category. We have compiled the top 5 most promising bug bounty platforms for those of you who are looking to enhance your existing software testing arsenal with knowledge and expertise from international security researchers:  1. HackerOne Being a unicorn backed by numerous reputable venture capitalists,  HackerOne  is probably the most well-known and recognized Bug Bounty brand in the world. According to their most recent annual report, over 1,700 companies trust the HackerOne platform to augment their in-house application security testing capacities. The report likewise says that their security researchers earned approximately $40 million in bounties in 2019 alone and $82 million cumulatively. HackerOne is also famous for hosting US government Bug Bounty programs, including ...

Google on Monday disclosed details about an ongoing campaign carried out by a government-backed threat actor from North Korea that has targeted security researchers working on vulnerability research and development. The internet giant's Threat Analysis Group (TAG) said the adversary created a research blog and multiple profiles on various social media platforms such as Twitter, LinkedIn, Telegram, Discord, and Keybase in a bid to communicate with the researchers and build trust. The goal, it appears, is to steal exploits developed by the researchers for possibly undisclosed vulnerabilities, thereby allowing them to stage further attacks on vulnerable targets of their choice. "Their blog contains write-ups and analysis of vulnerabilities that have been publicly disclosed, including 'guest' posts from unwitting legitimate security researchers, likely in an attempt to build additional credibility with other security researchers,"  said  TAG researcher Adam Weide...