Search
rag-inject-guard
Fevzi Ege Yurtsevenler <[email protected]>
RAG indirect prompt injection guard: scan retrieved documents for prompt-injection (instruction override, system/tool-prompt manipulation, exfiltration, invisible-Unicode/homoglyph smuggling) in English and Turkish, and quarantine poisoned docs before they reach the model.
...morecreate-agentic-workflow-kit
klaux
Reusable Codex workflow kit and project generator for spec-driven agentic development.
zxcvbn
wheels
realistic password strength estimation
chaosify-kubernetes
nahaap
Deterministic CLI for Kubernetes Continuous Control Verification
tbn-agent-network
Burhan Yanbolu
Trust-verified communication network for AI agents. The governed internet for AI.
curiosity-cat
markcleary
AI agent safety framework — standing orders, danger maps, and stories that teach cats to land on their feet
data-diode
Fionn Fitzmaurice
Send and receive data over serial diode
@nickelfox-technologies/nfx-guidelines
vedprakash-nickelfox
nfx-guidelines — Nickelfox engineering standards. Drops stack-aware guidelines (React, Next.js, Node.js, Python, React Native, PHP) into a project, wires them into Claude Code / Cursor / Copilot, and enforces pre-PR gates (vulns, outdated, secrets, tests)
...morex190
unempyd
Does this MCP endpoint serve its tool list to an unauthenticated caller? A runtime probe that emits a signed receipt of what it observed.
...moreCruiser Agent
TJR181
面向 CTF 竞赛评测平台（TSec Benchmark）的自动化 Web/逻辑漏洞挖掘与利用 Agent：分层调度 + 多会话并发 + 跨会话共享黑板 + 平台权威校验
neuralscan
ronby1
Auto-detect AI agents, MCP servers, and data connectors on your machine and visualize them as a live neural map with governance, data classification, and behavioral anomaly detection
...more@depup/dotenv-expand
chiefmikey
Expand environment variables using dotenv (with updated dependencies)
@anren-utils/mcp-audit
developer-anren
Model Context Protocol audit tool for analyzing project dependencies and generating audit reports
prompt-shield-ai
prompt-shield contributors
Self-learning prompt injection detection engine for LLM applications
io.github.vinaybhosle/agentstamp
Identity certificates, public registry, and wishing well for AI agents — x402 micropayments on Base
@ramblip/auth-action-rate-limiter
ramblip
A modular, policy-driven, in-process rate limiter for abuse prevention in sensitive auth flows
@twosense/n8n-nodes-twosense
tjhorner
n8n community node for Twosense continuous authentication and behavioral biometrics API
repomri
qi.liao
A zero-dependency MRI scan for your AI coding agent attack surface.
Wirken
gebruder
The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.
...moreclawwall
shauryatoor
Policy firewall for OpenClaw — intercepts every tool call, blocks dangerous operations, and protects your files and credentials across any task the AI performs.
...more