Search
hashon
felixlind
Encrypt, decrypt and hash JSON data with AES and SHA — made for secure local files and syncing.
@jaimilgorajiya/password-utils
jaimilgorajiya
A robust Node.js package for secure password hashing, validation, comparison, and login rate limiting.
@agently-org/sdk
ai-agently
A fully-typed TypeScript SDK for SaaS applications to securely encrypt and send authentication tokens to Agently
cybermes-mcp
Zyrexnn
Zero-Go Model Context Protocol (MCP) Server for Cybermes Autonomous Security & Diagnostic Framework
safeclaw
dino_safeclaw
Security management dashboard for AI agents – intercept, monitor, and control what AI agents can do on your system
genaiscope
Sapan Mohanty
Open-source Python toolkit to inspect, test, secure, optimize, and operationalize GenAI applications before production.
cascade-scan
cascade
AI Agent security evaluation framework — automated red-teaming for LLM tool-call governance.
attack-graph-analysis
Attack Graph Analysis: a security toolkit for weighted directed networks (Bellman-Ford, Menger, CVSS).
anastasis
bugbounties
High-performance JavaScript file crawler and endpoint discovery tool for bug bounty and security research
mcp-bastion-deepseek
Viquar Khan
MCP-Bastion security middleware for DeepSeek AI. Prompt injection, PII, and rate-limit protection.
@capsulesecurity/clawguard
lidanhazoutcapsule
Security guard plugin for OpenClaw - uses LLM as a Judge to detect and block risky tool calls
Agentic Redteam
Muneeb7860
Target-agnostic adversarial security testing harness for AI agents taking real-world actions
@andersmyrmel/vard
andersmyrmel
Lightweight prompt injection detection for LLM applications. Zod-inspired chainable API for prompt security.
@airlockapp/openclaw-airlock
aliozgur
Airlock security gateway plugin for OpenClaw — enforces human-in-the-loop approval for AI tool use
palaryn
palaryn
Palaryn - Model-agnostic infrastructure layer for AI agent I/O security, cost control, and observability
@jpsabent/ag-kit
jpsabent
AI Agent templates — Skills, Agents, and Workflows for enhanced coding assistance (security-hardened fork)
guardrail-agent
promptandbuild
Pre-execution security for AI coding agents. 18 guards that block dangerous commands before they run.
agentsec
markeljan
Security auditing CLI for AI agent skills — OWASP Agentic Skills Top 10 (AST10)
aipatrol
Denis Semenov
Security scanner for AI agent codebases: deterministic static core + optional LLM review brain
pentestcode
PentestCode Contributors
An agentic, workflow-driven pentesting CLI. Claude Code-style architecture for authorized offensive security.