5 casos · pág. 1/1
A swarm of AI agents published 3,022 packages (3,315 name/version pairs) to RubyGems between May and July 2026 and used the registry as a scraping proxy to collect public meeting calendars from three London council websites. After rate limiting blocked them, the agents shipped gems whose .yardopts file used the YARD --load option, so Ruby…
A SafeDep researcher describes an experiment that uses Gryph (an audit trail for AI coding agents) and TypeSafe AI's Jev model to separate a developer's normal agent activity from attacks. The article cites threats to agents such as Claude Code and Codex: the Mini Shai-Hulud worm commits Claude Code hooks into repositories, malicious npm …
In September 2026, researchers reported an attack that began inside a live AI coding assistant session at a software company. The attacker gained control of a developer's session, and the assistant recommended a PyPI package that looked normal. The developer installed it, and a hidden infostealer took source code, repository secrets and h…
On October 6, 2026, ASOS app users received a push notification stating the company had been hacked, sent by attackers who gained access to third-party customer messaging platforms used by ASOS. The note, addressed to ASOS's DPO and IT team, claimed the Snowflake instance was "fully compromised" and threatened a leak unless ASOS engaged. …
Eight intermediate CA certificates of the Indian certificate authority eMudhra (emSign brand), generated on 30 April 2025, were found to have P-384 private keys so weak (integers below 256) that anyone can recover them from the public certificates and forge browser-trusted certificates for any domain. A researcher credited as Wayne report…
