Search
stik-cli
jackadamslovell
Passive network watcher — tells you in plain English what's on your network, and taps you on the shoulder when something new shows up.
...moreAS AIAgent
awab-ml
A system-level defense framework for AI agents that intercepts and blocks indirect prompt injection attacks using strict instruction provenance and dynamic policy enforcement.
...moreinjectionshield
LaVon Rutledge
Rule-based prompt injection detection for LLM agents. Zero dependencies, no ML, no network.
@anticlaude/engine
AntiClaude
AntiClaude core engine: agent red-team evals, report compare, local guard, and runtime policy
caplabel
arisrhiannon
Offline, zero-dependency static capability analyzer for JavaScript — see what a script can do (network, filesystem, exec, secrets) before you run it.
...more@aikidosec/broker-client
GitHub Actions
Aikido Broker Client - Runs in customer network to forward requests to internal resources
zboralski/ida-headless-mcp
zboralski
🏎️ 🐍 🏠 🍎 🪟 🐧 - Headless IDA Pro binary analysis via MCP. Multi-session concurrency with Go orchestration and Python workers. Supports Il2CppDumper and Blutter metadata import for Unity and Flutter reverse engineering.
...moremgc-blackbox
Local encrypted execution base for multi-agent, cross-node, privacy-preserving task execution.
Agent Skills
ckanner
A curated collection of Claude Agent Skills designed to enhance AI workflows with specialized capabilities.
@uniglot/wont-let-you-see
uniglot
OpenCode plugin that masks sensitive cloud infrastructure data (AWS, Kubernetes) from LLMs
mcp-fence
yjcho9317
The bidirectional firewall for MCP — scans inputs AND outputs, detects rug-pulls at runtime, zero config.
trufflehog-js
maloma7
TypeScript wrapper for TruffleHog secret scanner
https-server
cp102
Basic https server that hosts a simple html page.
eslint-plugin-ai-guard
yashjadhav
ESLint plugin to catch AI-specific code patterns: missing error handling, async misuse, auth gaps, and hallucinations
vt-agent-firewall
Valentín Torassa Colombero
A fail-closed gateway between an AI agent and its tools: normalize, default-deny policy, human approval, append-only audit.
...morezinja-coder/apktool-mcp-server
zinja-coder
🐍 🏠 - APKTool MCP Server is a MCP server for the Apk Tool to provide automation in reverse engineering of Android APKs.
...moreagent-trust-telemetry
agent-trust-telemetry contributors
Trust telemetry middleware for inter-agent communication — makes instruction contamination observable across traces
lyrie-atp
overthetop
Agent Trust Protocol (ATP) — the cryptographic standard for AI agent identity, scope, and action verification. Reference implementation.
...moreagent-zero-trust
Rafael Pena
Zero-trust repo intake for AI coding agents: scan the instruction environment before Claude Code, Cursor, Codex, or Gemini touches a repo.
...morejwt-transform
restuwahyu13
transform your real jwt token into fake jwt token.