Vulnerability · Published Oct 12, 2026 · Assigned by VulnCheck

CVE-2026-109331Network-AI 5.14.0 before 5.15.2 Deny Pattern Bypass via ClaudeHookBridge extractFullTarget

High 7.4

In plain English

A high-severity security flaw in Network-AI from Jovancoding. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 3% of all known vulnerabilities).

Severity (CVSS 3.1)7.4High

Exploit odds (30 days)0.1%top 97.0% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
Jovancoding	Network-AI	5.14.0 – before 5.15.2

Weakness: CWE-436 · Vector: CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

References

GitHub Security Advisory (GHSA-9p2w-prp8-5722) vendor-advisory
VulnCheck Advisory: Network-AI 5.14.0 before 5.15.2 Deny Pattern Bypass via ClaudeHookBridge extractFullTarget third-party-advisory