NEAR AI says an attacker exploited a remote code execution flaw in SGLang on 8 November, reached 18 agents and about 100 accounts, and could have seen confidential-mode requests.
The latest AI security developments, threats, and industry updates.
NEAR AI says an attacker exploited a remote code execution flaw in SGLang on 8 November, reached 18 agents and about 100 accounts, and could have seen confidential-mode requests.
Apiiro found 1,122 public copies of .claude/settings.local.json holding at least one secret, saved when developers chose Yes, and don't ask again on commands containing passwords or keys.
Fireworks AI says billing data, secrets, datasets and incomplete model weights were affected, with evidence linking an LLMjacking group. A second intrusion followed on 23-24 October.
Kaspersky describes attackers using the open-source CyberStrikeAI framework, where a server-side LLM plans post-exploitation. Victims included education organizations.
OpenAI's GPT-6 Cyber system card reports 48.45% on ExploitGym and a Critical cyber rating, with limited Daybreak Red access and new safeguards, all by OpenAI's own account.