ChatGPT’s Memory Feature Supercharges Prompt Injection
The “ZombieAgent” exploit makes use of ChatGPT’s long-term memory and advanced capabilities.
The “ZombieAgent” exploit makes use of ChatGPT’s long-term memory and advanced capabilities.
A new campaign named GhostPoster has leveraged logo files associated with 17 Mozilla Firefox browser add-ons to embed malicious JavaScript code designed to hijack affiliate links, inject tracking code, and commit click and ad fraud. The extensions have been collectively downloaded over 50,000 times, according to Koi Security, which discovered the campaign. The add-ons are…
Overview of the PlayPraetor Masquerading Party Variants CTM360 has now identified a much larger extent of the ongoing Play Praetor campaign. What started with 6000+ URLs of a very specific banking attack has now grown to 16,000+ with multiple variants. This research is ongoing, and much more is expected to be discovered in the coming…
More than 41,000 ESXi instances remain vulnerable to a critical VMware vulnerability, one of three that Broadcom disclosed earlier this week.
The high-profile information stealer switches up its TTPs, but keeps the CAPTCHA tactic; we take a deep dive
BeyondTrust has patched all cloud instances of the vulnerability and has released patches for self-hosted versions.
A new set of four malicious packages have been discovered in the npm package registry with capabilities to steal cryptocurrency wallet credentials from Ethereum developers. “The packages masquerade as legitimate cryptographic utilities and Flashbots MEV infrastructure while secretly exfiltrating private keys and mnemonic seeds to a Telegram bot controlled by the threat actor,” Socket researcher