20-pass adversarial audit protocol for vibe-coded software

MCP server for adversarial security research — 6-phase pipeline from profile to disclosure

Capabilities-based adversarial code review and analyst triage CLI for git diffs.

generic/semantic/adversarial fixtures + adapter contract tests

Adversarial pre-deployment gating for autonomous AI agents.

Provider-neutral adversarial conformance for agent security plus A2A, MCP, Arazzo, and WebMCP standards.

Adversarial post-execute evaluation skill for pi — verifies implementation against contract, GAN-inspired

Contract-derived adversarial tests, runtime-matrix response conformance, and cookie-aware in-process sessions for Nifra apps.

EthersFlow TypeScript SDK & Cloudflare Worker helpers for Multi-Model Adversarial Consensus

Host-neutral adversarial white-box and black-box auditing agent CLI wrapper

Adversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock

Adversarial testing suite: a separate pass that writes unit + E2E tests from an independent, spec-only perspective to catch bugs the author/planner missed.

Algorithmic Agent Harness (ADR-047) — a deterministic control plane that wraps any model/tool/skill as a replaceable worker: utility-scored decisions, four-gate safety, hash-chained receipts, circuit-breaker recovery, adversarial verification, and a bandi

Model Context Protocol (MCP) server for EthersFlow — run proposed agent actions through federated adversarial multi-model consensus before executing them.

The smith that forges specs into merged PRs — autonomous AI implementer + adversarial reviewer, pluggable engines, human gate on critical paths.

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.

VIGIL -- Adversarial intelligence benchmark for AI governance platforms. 148 scenarios across 14 threat categories.

MCP (Model Context Protocol) server for Nexus Legal — exposes 27 specialised legal capabilities (analyze, consulta, draft, audit, consensus, monte_carlo, doctrina, opinion, redteam, adversarial, cross_border, jurisprudencia_search, verify_cita, verificaci

Packaged multi-agent adversarial code review for DeepSeek Harness — one finder per lens in parallel, then a verifier per finding whose task is to refute it, so only confirmed defects are reported.

Official TypeScript SDK for Lakera Red — run adversarial scans against your AI agents and chatbots.