CVE-2026-109331

HIGHCVSS 7.4/10

Last modified

CVE-2026-109331 is a high-severity vulnerability rated 7.4/10 on the CVSS scale. 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..

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.

Metrics

Weakness Enumeration

References

Timeline

Published
Last Modified
Status
Deferred

Frequently Asked Questions

What is 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.
How severe is CVE-2026-109331?
CVE-2026-109331 has a CVSS score of 7.4/10 (HIGH severity).
How do I fix CVE-2026-109331?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

Are you affected by CVE-2026-109331?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST