Jeff Emanuel dcg Resource Management Error Vulnerability

Jeff Emanuel’s dcg versions prior to 0.6.6 contain a security vulnerability. This vulnerability stems from nested or unclosed $ or $ sequences that are recursively re-scanned after the internal scan has terminated, leading to exponentially long processing times and causing the suspended PreToolUs...

CVE-2026-109331

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...

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...

CVE-2026-109331 Network-AI 5.14.0 before 5.15.2 Deny Pattern Bypass via ClaudeHookBridge extractFullTarget

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...

CVE-2026-109331

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...

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...

CVE-2026-109331 Network-AI 5.14.0 before 5.15.2 Deny Pattern Bypass via ClaudeHookBridge extractFullTarget

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...

PT-2026-110748

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...

CVE-2026-109331: Interpretation Conflict

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...