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.
2026年10月13日
CVE-2026-109331 [HIGH] – Network-AI from 5.14.0 before 5.15.2 contains a security control bypass vulnerability in t
📑 文章目录



