All vulnerabilities
CVE-2026-109331GHSA-9p2w-prp8-5722

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

Jovancoding Network-AI
CVSS
7.5High
ExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV
Exploit odds (EPSS)0.14%Chance of exploitation activity in the next 30 days, higher than 2% of CVEs. Scored 23 Oct 2026FIRST EPSS
Fixed in5.15.2Fixed versionCVE List
Published12 Oct 2026Updated 12 Oct 2026CVE List

What fixes it

A fixed version on one release line is not the upgrade target for every line. Check your exact version and any vendor backports.

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.

Text from CVE List

Affected versions 2

  • Network-AIaffected: 5.14.0 before 5.15.2CVE List
  • Network-AIunaffected: 5.15.2CVE List

References 2