CVE-2026-109331

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.

Score

CVSS 4.0 7.5 High

Status

Deferred - disclosure@vulncheck.com

Published

2026-10-12

Last modified

2026-10-26

Weaknesses

CWE-436

Affected products

• Network-ai (Network-ai)

References

• https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-9p2w-prp8-5722
• https://www.vulncheck.com/advisories/network-ai-5.14.0-before-5.15.2-deny-pattern-bypass-via-claudehookbridge-extractfu…