{"vulnerability": "cve-2026-54051", "sightings": [{"uuid": "a9fa5a87-e55b-4751-afd6-5a4f36ac9432", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "86ecb4e1-bb32-44d5-9f39-8a4673af8385", "vulnerability": "CVE-2026-54051", "type": "published-proof-of-concept", "source": "https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-qw6v-5fcf-5666", "content": "", "creation_timestamp": "2026-06-02T20:40:48.000000Z"}, {"uuid": "2b2ec4b4-1fc5-4f2e-8471-03be427b522d", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2026-54051", "type": "seen", "source": "https://bsky.app/profile/stackflag.bsky.social/post/3mr3tqdty562a", "content": "CVE-2026-54051 - network-ai\nA security issue in Network-AI allows malicious commands to be executed if they match a wildcard allowlist. This could allow an attacker to run arbitrary code on a\u2026\n\nToo many irrelevant or confusing CVEs? Use stackflag.com\n\n#networkai #jovanrocks #npm #CVE #infosec", "creation_timestamp": "2026-07-20T17:42:05.050415Z"}, {"uuid": "5157ee74-4097-475b-9445-f9ceb6ccb0e0", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2026-54051", "type": "seen", "source": "https://bsky.app/profile/cve.skyfleet.blue/post/3mr3xmfzsmt2g", "content": "CVE-2026-54051 - Network-AI has an an OS Command Injection issue\nCVE ID : CVE-2026-54051\n \n Published : July 20, 2026, 5:17 p.m. | 26\u00a0minutes ago\n \n Description : Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to version 5.9.1, the agent sandbox gates shell...", "creation_timestamp": "2026-07-20T18:51:27.375893Z"}, {"uuid": "a83f6fd2-bceb-45dd-8dc9-2e9522812732", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "cve-2026-54051", "type": "seen", "source": "https://bsky.app/profile/gleephoenix.bsky.social/post/3mravyjetb32e", "content": "@cve.skyfleet.blue cve-2026-54051 network-ai command injection issue \u2014 Browser actions get scoped creds + action logs \u2014 the DOM surface is the real trust boundary. How are you scoping creds for in-page agents today? https://platform.gleephoenix.com/intake", "creation_timestamp": "2026-07-22T18:05:44.919878Z"}]}