Search

Guarded vector-database client wrapper for BonkLM — validation, secret and injection guardrails around a self-hosted vector search engine

Encrypt/Decrypt the values of a given object

Scan your cloud infrastructure data and query it with GraphQL

Local prompt injection and jailbreak detection for LLM applications

Red-team your RAG pipeline for prompt injection and source-document leakage, in CI.

npm supply chain attack defense via execution isolation

Suno AI music generation plugin for ElizaOS - Enables AI-powered music creation and audio manipulation

A local, provider-agnostic agent CLI — LangGraph.js core, Ink TUI, durable sessions, human-in-the-loop approvals, built-in evals.

Turkish and multilingual prompt-injection / jailbreak probes for NVIDIA garak (LLM vulnerability scanner).

Security Lib

Check what an LLM is given for prompt injection: material at ingest, and the turn it answers

Content guardrails for LLM applications, with published precision and recall and provenance on every decision.

autonomous black-box web penetration testing. give it a URL, it finds everything exploitable.

Authensor guardrail adapter for OpenAI Agents SDK

A comprehensive React Native security checker that detects jailbreak, root, emulators, hooks, tampering, and other security threats

A security baseline for JavaScript, TypeScript and Python projects: pre-commit hooks, CI checks, hardened Docker config and AI-assistant rules, plus a plain-language security check.

Security assistant plugin by Alibaba Cloud that provides LLM request/response protection, tool call security checks.

Enterprise-grade security module for frontend and backend applications with comprehensive protection against XSS, CSRF, SQL injection, and other security vulnerabilities

Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible

Catch missing RLS, GRANT and REVOKE in Supabase migrations before they ship — tables without row level security, SECURITY DEFINER functions callable by anon, REVOKEs that hit the wrong overload, and tables your client reads but never granted.