OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach

OpenAI on Tuesday revealed the rogue artificial intelligence AI agent that escaped its sealed evaluation environment and broke into Hugging Face's production environment also hacked multiple third-party accounts and services as part of the attack. The latest disclosure shows that the security...

CVE-2026-47255

The CVE-2026-47255 entry concerns AgenticMail API/core vulnerabilities in versions prior to 0.9.32 and 0.9.10, respectively. The connected documents specify multiple hardening and validation weaknesses across storage and outbound relay handling, including: (1) validation and binding of inactive-a...

Malicious code in proxy-check-i (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 2da390c130eb840eb129a5d43faf0a64a0f0f602070243613aa0e2f8ea8f6d04 The package advertises itself as a wrapper for a 'qsshd executable' but the bundled Go binary is a reverse-SSH daemon that grants a remote operator...

MAL-2026-10100 Malicious code in proxy-check-i (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 2da390c130eb840eb129a5d43faf0a64a0f0f602070243613aa0e2f8ea8f6d04 The package advertises itself as a wrapper for a 'qsshd executable' but the bundled Go binary is a reverse-SSH daemon that grants a remote operator...

GHSA-WJJV-3MJ2-39HF AgenticMail API/storage and outbound relay hardening fixes

The current upstream main branch at commit 7e0206d was reviewed, and the fix-first patch set was rebased on 2026-05-18. The patches cover: validated and bound inactive-agent hour filtering; storage SQL identifier validation; metadata-backed ownership checks for raw storage SQL; blocking direct...