CVE-2026-109331 Network-AI 5.14.0 before 5.15.2 Deny Pattern Bypass via ClaudeHookBridge extractFullTarget
Attackers can bypass deny patterns in Network-AI by hiding malicious payloads in secondary fields, enabling code execution or web shell uploads.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-109331?
CVE-2026-109331 is a high-severity vulnerability in Jovancoding Network-AI, published on 12 Oct 2026. It can only be exploited from the same machine or local network, with no action from the victim.
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.
Weakness: CWE-436
Which versions are affected by CVE-2026-109331?
How do I fix CVE-2026-109331?
No fix has been published for CVE-2026-109331 yet. Limit exposure of the affected software until one is available.
Is CVE-2026-109331 being exploited?
There is no known exploitation of CVE-2026-109331 in the wild and no public exploit code.
Sources
Also known as GHSA-8x93-4278-4f5c, GHSA-9p2w-prp8-5722.