Defense handles permissions for document storage database objects.

SSRF defense library for Node.js with safe URL validation utilities.

Prompt injection defense framework for AI tool-calling

The Defense Deva handles all the various defense in Deva.world.

JupiterOne managed integration for Carbon Black Defense.

AI Manipulation Defense System (AIMDS) with self-learning, prompt injection detection, and vector search integration

Full Court Defense CLI — security scanning for AI agents from your terminal

Secure-by-default MCP server with 5-layer validation for defense-in-depth protection

Pure middle-message removal with tool-use/result orphan defense

WorldWideView plugin — Known Air Defense Identification Zones (ADIZ) and boundaries.

Declaw provider for ComputeSDK - secure sandboxes with PII scanning, prompt-injection defense, and network egress filtering

Phasegate — AI-agnostic quality defense toolkit. Enforces structural integrity between design intent and code.

Academic skill pack — dissertation review, question generation, document checking for thesis defense (ГЭК). Contains only evaluation criteria and methodology, no student data.

Secure runtime for AI agents - isolated sandboxes with network isolation, PII scanning, prompt injection defense, and egress filtering.

LLM-as-judge grader with prompt-injection defense and structured tool-use output

Generic HTTP fetch tool with fail-closed origin allow-list, SSRF defense, and credential stripping

This adapter integrates with system described as: Cisco Defense Orchestrator.

This adapter integrates with system described as: Infoblox Threat Defense.

AI Defense System — Production-ready security middleware for protecting AI applications from prompt injection, manipulation attacks, PII leakage, and adversarial inputs. Available as both 'aidefence' (British) and 'aidefense' (American).

Cascading content protection engine — PII detection, secret scanning, prompt injection defense