Bluefire Redteam scanner for Nx 's1ngularity' supply-chain compromise (malicious versions, IoCs, exfil).

AI Safety & Red Teaming Toolkit for proactive security testing of AI agents

Servidor MCP (Model Context Protocol) de Nexus Legal — expone 27 capabilities jurídicas (analyze, consulta, draft, audit, consensus, monte_carlo, doctrina, opinion, redteam, adversarial, cross_border, jurisprudencia_search, verify_cita, verificacion, plaz

Red-team adversarial security testing for ArtemisKit LLM evaluation toolkit

Autonomous red team tool for MCP servers. Finds exploitable vulnerabilities before attackers do.

Multi-agent red teaming system for Pi - 10 specialized security agents for vulnerability assessment and penetration testing

Authorized red-team harness for AI agents and LLM targets

Open-source CLI toolkit for automated red-teaming of LLM-powered applications

Placeholder — bootstrapper for the AI-CSL MCP Red-Team Workbench. Real release lands in v0.4. Reserves the package name. See https://github.com/botz-pillar/mcp-redteam-workbench

AI vs AI adversarial security testing platform. Red team agents attack, blue team agents defend. Fully automated.

AxioRank agent red-team corpus: a versioned library of attack scenarios (secrets, injection, destructive ops, kill chains) plus benign controls. Pure data, zero runtime dependencies.

Adversarial red-team test seeds for AI agent safety evaluation — 15 attack patterns across 5 categories mapped to MITRE ATLAS

SquatGuard MCP Template for Python

P3.5a red-team test framework for the Brainstorm endpoint-agent sandbox abstraction. Runs a configurable battery of probes (A1-A10 attacker classes) against any concrete Sandbox implementation (CHV, VF, mock) and emits a structured RedTeamReport. Validati

fastpace — trust harness for AI-assisted development. Installs skills, agents, hooks, and guardrails into any repo.

Command-line interface for ArtemisKit LLM evaluation toolkit

<!-- Generated file — edit the source area record and regenerate; do not edit by hand. -->

Catch what your AI coding agent missed before merge with local PR safety checks

Open-source CLI for PR regression-risk, blast-radius, and code-decay analysis

Shomra — adversarial assurance for AI agents, as a local-first CLI. Blocks dangerous tool-calls before they run, attacks your own guardrails to prove they hold, and gates AI artifacts in your editor and CI.