security

Open-source security guidance for specific libraries and versions, aimed at developers and coding agents. The repo includes local setup steps, a web site, and an installable skill for agent workflows.

Open-source endpoint visibility and response for AI agents, with local detection, optional pre-action blocking, and forensic reconstruction.

Local-first MCP gateway that lets multiple AI clients share one server setup, with lazy tool discovery to reduce token usage and built-in tool integrity and quarantine controls.

Exfault is an autonomous Android security testing tool that uses AI agents, static analysis, dynamic analysis, authenticated workflows, and cloud emulators to produce reproducible findings and reports.

A honeypot telemetry and threat intelligence service with searchable IP lookups, recent scanner data, and an MCP/JSON-RPC API for agents and developers.

Weir is a CI gate for AI agents that reads OpenTelemetry traces and fails builds when sensitive data reaches forbidden sinks. It includes a gauge for trace coverage, taint tracking, HTML reports, and rule-based scans for agent workflows.

CLI and GitHub Action that scans repos, logs, and CI artifacts for leaked LLM reasoning-trace blocks from Anthropic, OpenAI, and Google.

Kotro is a local control plane for coding agents that governs MCP tool actions and LLM traffic with one binary. The page shows install options, supported clients, dashboard access, and concrete controls like schema pinning, redaction, cache, budget, and circuit breaker behavior.

An open-source agent-driven package manager for versioned, checksummed, approval-gated tasks run through Claude Code, Codex, Gemini CLI, OpenCode, or Antigravity.

Hotcell is a self-hostable sandbox SDK for AI agents that runs isolated sandboxes on local hardware or servers. The page shows setup, CLI commands, key handling, egress control, and support for containers or microVMs.

A local Rust-plus-Python middleware layer for LLM apps that claims to reduce token usage and add in-process security checks before prompts are sent to a provider.

A loopback HTTPS proxy that swaps placeholders for real API keys at request time, keeping secrets out of the agent process. It uses Bitwarden Secrets Manager and supports scoped bindings for hosts, methods, and paths.

Runtime authorization platform for AI agents with open-source SDKs in Python, TypeScript, Go, Java, and Rust. The page says the hosted service is in production, supports per-action checks, scoped delegation, revocable tokens, and a shared authorization model across MCP tools, agent-to-agent calls, and direct API integr

A minimal native macOS sandbox for running Claude Code or Codex with OS-enforced limits on what the agent can touch.

An open-source reference implementation for autonomous vulnerability discovery and remediation with Claude. It includes Claude Code skills for threat modeling, scanning, triage, patching, plus a harness for running a recon → find → verify → report → patch pipeline.

Open-source security scanner and firewall for MCP servers. It scans configs for common MCP risks, enforces runtime policies on tool calls, and produces audit logs, with CLI commands, policy examples, and a programmatic API.

A secure Model Context Protocol server that gives AI assistants controlled terminal access with risk analysis, sandboxing, logging, filesystem protection, and optional Docker and Git features.

An interactive lab for tracing how AI-assisted engineering workflows can reach repos, CI/CD, credentials, tools, approvals, and proof trails.

Runtime governance and containment for AI agents. Faramesh sits between an agent and its tools to enforce policy checks, approval steps, credential isolation, and tamper-evident audit logs before risky actions execute.

A security product for Claude Code that reviews application architecture inside the IDE via MCP, with contextual assessments, prioritized mitigations, and continuous re-checks as the codebase changes.

Sentrint is a security scanner for apps built with LLM platforms like Bolt, Cursor, and v0. It scans repos for secrets, access rules, vulnerable dependencies, and risky code paths, then returns plain-English findings and a copy-paste fix prompt.

A lightweight shell-based guard that blocks destructive commands before an AI coding agent can run them. It targets risky actions like git reset --hard, rm -rf, force-pushes, and destructive cloud/database commands, with local regex rules and a test script.

A CLI for running untrusted MCP servers in sandboxed containers with deny-by-default egress, traffic watching, and host approval workflows. It can also compose servers into agents and expose them over OCI registries.

A harness that runs MCP servers in a disposable Linux sandbox and logs their real startup behavior, including file access and outbound network connections.