Search
o1op
A deterministic code synthesis operator — composes working programs from natural-language intent without any LLM in the loop. 8-color algebraic type system over a 7-pass causal knowledge graph, with a 7-layer verification pipeline and an autonomous 9-phase engagement operator.
...more@fastify/secure-session
matteo.collina
Create a secure stateless cookie session for Fastify
auto-smart-security
haivinh
Production-ready security middleware for Express / NestJS
Agent Bypass
1837620622
AgentBypass — Omni Operator LLM Agent Skill (Cknb): Turn any LLM into RE / Pwn / CTF / Pentest / Protocol / Crypto / Mobile / Forensics operator. 20 modules, zero-dependency, all agents.
...morecodedrift
hamzzaamalik
Guardrails for AI-assisted development - Detects IDOR, missing input validation, hardcoded secrets, and other critical bugs in AI-generated code
...moreAegisgate Agent Firewall
myceldigital
Personal AI agent firewall skill for blocking prompt injection, unsafe tool calls, data exfiltration, malicious skills, and memory poisoning.
...moremcp-guardrails
Drop-in deterministic policy layer for MCP-using AI agents
security-context
mattcollier
Security Context
sovereign-shield
Mattijs Moens
Production-grade AI defense — deterministic filters + optional LLM veto verification.
mvar-security
Shawn Cohen
MVAR: Information Flow Control for LLM Agent Runtimes
pi-npm-security
GitHub Actions
Pi package for npm/supply-chain security workflows: Socket MCP bridge extension, npm security best-practices skill, and related tooling.
...morecontextfence
GitHub Actions
Playwright for RAG permissions — prove restricted context stays restricted.
io.github.KubaOpoczka/tripwire-guard
immkuba
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
pyveil
Local PII and secret redaction for Python LLM apps, AI agents, tool calls, and MCP
@neurosec/sentry
support_neurosec
NeuroShield Sentry — host-level agent protection daemon. Detects and blocks malicious AI agent actions at the OS level.
@sideband/cloud
GitHub Actions
Cloud relay SDK for Sideband: connect clients and daemons via relay.sideband.cloud with automatic session management, token renewal, and E2EE.
...moreagentic-workflow-guard
guorunjie
Semgrep-style static analysis for AI automation workflows: find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.
...more@majikah/majik-message
thezelijah
Post-quantum end-to-end encryption with ML-KEM-768. Seed phrase–based accounts. Auto-expiring messages. Offline-ready. Exportable encrypted messages. Tamper-proof threads with blockchain-like integrity. Quantum-resistant messaging.
...more@senad-d/guardme
senad-d
Deny-first Pi guardrails that keep LLM shell and file access safe, transparent, and user-approved.
AgentWard
FIND-Lab
AgentWard – Built for all, hardened for OpenClaw.