2 matches found
EUVD-2026-97633
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...
7.5CVSS5.9AI score0.00135EPSS
SaveExploits0References2
CVE-2026-109331
Network-AI versions 5.14.0 before 5.15.2 contain a security control bypass vulnerability within the ClaudeHookBridge PreToolUse hook . The root cause is that the system matches deny patterns only against the first present candidate field. This allows a prompt-injected agent to bypass security res...
7.5CVSS6AI score0.00135EPSS
SaveExploits0References2
20