CVE-2026-109331

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

Published Oct 12, 2026 CVSS 4.0 · 7.5 High EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

Network-AI versions 5.14.0‑5.15.1 contain a vulnerability in the ClaudeHookBridge PreToolUse hook that applies deny patterns to only the first candidate field. An attacker controlling a prompt‑injected agent can insert malicious payloads into fields such as Write content or an MCP script parameter alongside harmless values like file_path or command, thereby evading the deny patterns and writing web shells or executing arbitrary scripts. This flaw permits attackers to gain execution privileges within the affected system, compromising confidentiality, integrity, and availability of applications running on Network-AI.

Affected Systems

The affected product is Jovancoding’s Network-AI software. Versions from 5.14.0 up to, but not including, 5.15.2 are vulnerable. Systems running any of these releases should be reviewed for potential exploitation.

Risk and Exploitability

The CVSS score of 7.5 indicates a high severity of this denial‑pattern bypass. Although no EPSS score is available, the exploitability is considered high because the attacker only needs to influence the agent’s prompt content, a scenario common in many AI‑assistant deployments. The vulnerability is not listed in the CISA KEV catalog, but its high CVSS and potential for arbitrary code execution make it a priority for rapid remediation. The likely attack vector is local to systems that host the Network‑AI agent, requiring the attacker to supply crafted prompt inputs to the agent process.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade Jovancoding Network‑AI to version 5.15.2 or later.
  • If upgrading immediately is not possible, restrict agent prompt injection to validated inputs and apply deny patterns to all candidate fields rather than only the first.
  • Enforce least privilege for agents, monitor for unauthorized script execution, and conduct regular scans for web shells.

Generated by OpenCVE AI on October 12, 2026 at 18:38 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
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.
Title Network-AI 5.14.0 before 5.15.2 Deny Pattern Bypass via ClaudeHookBridge extractFullTarget
First Time appeared Network-ai
Network-ai network-ai
Weaknesses CWE-436
CPEs cpe:2.3:a:network-ai:network-ai:*:*:*:*:*:*:*:*
Vendors & Products Network-ai
Network-ai network-ai
References
Metrics cvssV3_1

{'score': 7.4, 'vector': 'CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H'}

cvssV4_0

{'score': 7.5, 'vector': 'CVSS:4.0/AV:L/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
VulnCheck
Published
Updated
Oct 26, 2026, 4:46 PM
Reserved
Oct 12, 2026, 2:18 PM
Status
Deferred
Published
Oct 12, 2026, 5:17 PM
Modified
Oct 26, 2026, 5:17 PM