Security research PoC marker for a coordinated package-hallucination (slopsquatting) disclosure to Anthropic via HackerOne. Benign: displays a banner, collects nothing, no network calls.

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic code review, auto-fix. For Claude Code, Cursor, Windsu

Real-time AI package hallucination and slopsquatting defense for AI coding agents

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix. For Claude Code, Cursor, Windsurf, Cline, OpenClaw.

OpenCode plugin that automatically resumes stalled LLM sessions when thinking/streaming freezes mid-generation.

Install the harness-engine Codex skill for initializing and reconciling advanced repository harness docs.

AI-powered research assistant with REAL Ed25519 cryptographic signatures, GOAP planning, and Perplexity API integration

IUMBTEMS (Epistemic Swarm) — High-Integrity Dialectic Research Agent Harness for Claude Code, OpenCode V2, Pi (pi.dev), OMP (oh-my-pi), Gemini CLI, Codex CLI, and AntiGravity

AI code verification CLI — find bugs that tests miss, linters ignore, and code review overlooks

Tribunal Kit is the governance layer for AI coding agents that stops AI hallucinations and npm ghost packages before they hit disk. Works with Cursor, Windsurf, Claude Code, and Aider.

Detects hallucinated packages (slopsquatting), exposed secrets, and language-specific injection vulnerabilities in AI-generated code. Covers npm, PyPI, crates.io, Packagist, Go modules, RubyGems, and Maven locally -- plus an optional connected advanced sc

Task-aware AGENTS.md context injection and compliance reporting for Codex, Claude Code, and Antigravity.

AI Output Verification Toolkit — Local-first LLM safety, hallucination risk signals, PII redaction, prompt injection defense, and runtime monitoring. Zero telemetry. OWASP LLM Top 10 aligned.

Minimalist MCP server + hooks for anti-hallucination in AI coding assistants. Detects hallucinated symbols, typos in imports, and invalid API routes via AST-based fuzzy matching.

Offline, in-process input/output safety guard for LLM apps (PII vault, prompt-injection, secrets, malicious URLs, package hallucination). Rust core, Node (napi) + edge/browser (WASM). Defense-in-depth, not a guarantee.

Lightweight, zero-Python security scanner MCP server for AI coding agents. Fast install (~5s), 1700+ vulnerability rules with pure JavaScript regex engine, 4.3M+ package hallucination detection. For Claude Code, Cursor, Windsurf, Cline.

Offline, in-process input/output safety guard for LLM apps (PII vault, prompt-injection, secrets, malicious URLs, package hallucination). Rust core, Node (napi) + edge/browser (WASM). Defense-in-depth, not a guarantee.

The LLM Evaluation Framework for TypeScript

Offline, in-process input/output safety guard for LLM apps (PII vault, prompt-injection, secrets, malicious URLs, package hallucination). Rust core, Node (napi) + edge/browser (WASM). Defense-in-depth, not a guarantee.

Offline, in-process input/output safety guard for LLM apps (PII vault, prompt-injection, secrets, malicious URLs, package hallucination). Rust core, Node (napi) + edge/browser (WASM). Defense-in-depth, not a guarantee.