{"vulnerability": "CVE-2026-30623", "sightings": [{"uuid": "ee8cc032-7ade-4dca-a687-7e2c39a3af48", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2026-30623", "type": "seen", "source": "https://bsky.app/profile/stackflag.bsky.social/post/3mqrhlonigc2y", "content": "CVE-2026-30623\nA security issue exists in LiteLLM 1.18.10 that could allow an attacker to execute malicious code on your server with the same permissions as the LiteLLM process. This can happen if an attacker is able to\u2026\n\nToo many irrelevant or confusing CVEs? Use stackflag.com\n\n#CVE #infosec", "creation_timestamp": "2026-07-16T14:38:05.569740Z"}, {"uuid": "6774b2e7-6e6e-4a9c-bd75-b3c992d1e0b1", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2026-30623", "type": "seen", "source": "https://bsky.app/profile/moez19.bsky.social/post/3mqu4qhknhb2i", "content": "Security note for AI infra folks: CVE-2026-30623 just landed -- a critical RCE in LiteLLM (1.74.2 to before 1.83.7) via stdio transport in MCP configs. Patched in 1.83.7-stable. If you route model calls through it, update today. #AIsecurity #LLM #DevOps", "creation_timestamp": "2026-07-17T16:01:54.100379Z"}]}