Anthropic Mythos AI Finds Rejetto HFS Flaw That Lets Attackers Forge Admin Sessions and Execute Code
Mythos AI found a critical Rejetto HFS flaw enabling admin-session forgery and arbitrary code execution via predictable Math.random() keys.
Two OpenAI Codex sandbox flaws, Overpatch and Heapjack, could let malicious repositories execute commands on developer systems.
Researchers escaped OpenAI's Codex sandbox two ways, one running commands on a developer's machine from its most locked-down mode. OpenAI has patched both.
status: waiting triageThis issue needs help from moderators and users to reproduce and confirm its validity and fix.This issue needs help from moderators and users to reproduce and confirm its ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results