Answer in brief
CVE-2026-109331 records a High severity (CVSS 7.5) vulnerability in Network-AI 5.14.0 before 5.15.2 Deny Pattern Bypass via ClaudeHookBridge extractFullTarget. The current sources do not mark it as known exploited. The current feed maps Jovancoding/Network-AI (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 7.5. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps Jovancoding/Network-AI (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| Jovancoding/Network-AIgeneric | >=5.14.0 <5.15.2 | 5.15.2 |
Published upstream
Oct 12, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Oct 12, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Oct 12, 2026
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.
Quoted source text, attributed separately from HOL analysis.