CVE-2026-109331

high

Description

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 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.

References

https://www.vulncheck.com/advisories/network-ai-5.14.0-before-5.15.2-deny-pattern-bypass-via-claudehookbridge-extractfulltarget

https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-9p2w-prp8-5722

https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-97633

Details

Source: Mitre, NVD

Published: 2026-10-12

Updated: 2026-10-26

Risk Information

CVSS v2

Base Score: 6.2

Vector: CVSS2#AV:L/AC:H/Au:N/C:C/I:C/A:C

Severity: Medium

CVSS v3

Base Score: 7.4

Vector: CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

Severity: High

CVSS v4

Base Score: 7.5

Vector: CVSS:4.0/AV:L/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Severity: High

EPSS

EPSS: 0.00135