{"id":"CVE-2026-109331","title":"Network-AI from 5.14.0 before 5.15.2 contains a security control bypass vulnerability in the ClaudeHookBridge PreToolUse hook, which matches deny patterns only against the first present candidate field","summary":"Network-AI from 5.14.0 before 5.15.2 contains a security control bypass vulnerability in the ClaudeHookBridge PreToolUse hook, which matches deny patterns only against the first present candidate field. A prompt-injected agent can place …","severity":"high","cvss":7.4,"cvssVector":"CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","cwe":["CWE-436"],"published":"2026-10-12","updated":"2026-10-12","sourceUpdated":"2026-10-12T17:17:28.970","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-109331","references":[{"url":"https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-9p2w-prp8-5722","label":"disclosure@vulncheck.com"},{"url":"https://www.vulncheck.com/advisories/network-ai-5.14.0-before-5.15.2-deny-pattern-bypass-via-claudehookbridge-extractfulltarget","label":"disclosure@vulncheck.com"}],"tags":["nvd"],"ingestedAt":"2026-10-12T18:00:08.204Z","slug":"CVE-2026-109331","body":"## Overview\n\nNetwork-AI from 5.14.0 before 5.15.2 contains a security control bypass vulnerability in the ClaudeHookBridge PreToolUse hook, which matches deny patterns only against the first present candidate field. A prompt-injected agent can place dangerous payloads in fields like Write content or an MCP script parameter beside a benign file_path or command, evading denyPatterns to write web shells or execute scripts.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.","depth":"twilight","depthScore":41,"depthScoreParts":{"impact":40.7,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}