-
Noma Labs found a high-severity Claude Code Desktop flaw that let malicious HTML files steal local credentials and…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Anthropic finds small AI models can set up inference servers across different hardware, raising concerns about future AI…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Check Point Research found two LiteLLM vulnerabilities that could let low-privilege users execute code, access sensitive files, hijack admin accounts, and steal AI provider API keys.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Cybersecurity firm Morphisec has uncovered a new Windows infostealer called RevStealer, which is being distributed through a fake…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
At Black Hat USA 2026, Novee found GitHub workflow flaws in Claude Code, Gemini CLI and Codex that enabled RCE, credential theft and agent control in pipelines.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Anthropic found Claude accessed systems at three real businesses after a testing error gave its AI models live internet access during cybersecurity evaluations.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Google Search indexed public Claude AI chat links, letting people find shared conversations through the site query before those listings disappeared soon after.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A one-click Claude Desktop flaw allowed attackers to submit concealed instructions without review, exposing chats and enabling code execution on some systems remotely.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Wiz found GhostApproval symlink flaws in major AI coding assistants that could hide sensitive file targets, bypass approval checks and enable system access too.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Fake ChatGPT desktop app ads pushed password-stealing malware by abusing trusted AI links, hiding from scanners, and tricking users into downloads.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
