Search
promptlock-py
Anti-prompt injection SDK for LLM applications
@shard-for-obsidian/cli
GitHub Actions
Shard CLI tool to push and pull plugins from GHCR
terramend-mcp-server
Gabriel Ignat
Model Context Protocol server for Terramend Cloud — read a repo's Terraform findings, health score, compliance evidence and crosswalk from Claude Code, Cursor or Windsurf.
...moremcp-medic
Shivam Dixit
Diagnose broken MCP (Model Context Protocol) server configs before they break your agent silently.
moltblock
moltblock
Framework for building evolving composite AI intelligences (Entities)
Patchwright
khiebel
Right to repair, for the connected home. Patch your own IoT firmware without waiting for the vendor's cloud rollout.
ai-ccproxy
Scriptable mitmproxy-based LLM API interceptor for Claude Code
cryptologin
Passwordless without Password Storage Authentication System - No Email, No Password, Just Your Secret
eslint-plugin-no-wildcard-postmessage
mozfreddyb
custom ESLint rule to disallows calling postMessage to wildcard targets
vulntriage
Nivish
Rank pip-audit CVEs by real exploitability using Claude AI
sector8-sdk
Python SDK for Sector8 AI telemetry, alerts, and MCP guard installation
graphql-cost-analysis
schrax
Graphql query cost analyzer. Use it to protect your GraphQL servers against DoS attacks, compute data consumption per user and limit it.
...more@lucascampooss/authcore
lucascampooss
Framework-agnostic authentication library with JWT, refresh tokens, RBAC, and advanced session management
sentinel-agent-trust-crewai
"Cosimo (plannest.net)" <[email protected]>
CrewAI adapter for Sentinel AI agent governance — wrap any CrewAI tool so every call is authorized (and audited) by the Sentinel gateway before it runs. Private beta: [email protected]
...morewickrio-example-app
pcushman
WickrIO Node.js API example app
envkey-webpack-plugin
envkey
Use envkey as a webpack plugin.
pykiwoom-rest
키움증권 REST API Python 래퍼와 CLI, MCP 서버
express-token-api-middleware
mallocator
An express middleware that allows to protect an api behind token authentication, rate limiting and endpoint permissions.
agent-sanitizer
GitHub Actions
Defend an agent against hidden-content injection: strip payload-capable invisible Unicode and ANSI, splice out human-invisible HTML, and flag data-exfil URLs in untrusted text before any model sees it.
...moretibetclaw
jaspervandemeent
Trust-First Agent Framework — behavioral trust, cryptographic provenance, semantic firewall. The trust kernel that agentic AI is missing.
...more