#devsecops

Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.

Production-ready Claude Code skills for cybersecurity — secret scanning, SAST, prompt-injection testing, HTTP/JWT/dependency auditing. Zero dependencies.

Open-source server that refuses vulnerable package installs. The backend the refuse CLI shim calls.

Dual-track AI reference architecture: RAG system design & AI Security Engineering (EN/ZH) | 双轨 AI 参考架构：RAG 系统设计与 AI 安全工程

Find where agent-controlled intent reaches consequential actions without an authority check. Python + TypeScript + Go. Zero-dependency SAST for AI agents.

Turn any public AI coding CLI (Claude Code, Codex, Gemini, Cursor, Cline, Aider, opencode) into your company's internal, audit-grade, white-labeled launcher — one structured interview, 15 cyber controls, 30+ audit rules, compliance .docx, universal cost tracking.

Offline, no-AI "safe to ship?" gate for vibe-coded apps — finds the security mistakes AI coding agents make (secrets, unprotected routes, eval-RCE, SQLi, CORS, JWT, leaked keys). CLI + MCP, agent-runnable.

Cross-agent security & quality hardening engine for Claude Code, Codex, and Gemini CLI. Enforces user-authored playbooks, verifiable evidence gates, and auditable readiness reports.

Claude Code scaffold for building AI platforms securely — agent/LLM security, Kubernetes, SRE, observability, identity, and supply chain, grounded in published framework canon (OWASP, NIST, CIS, SLSA). Data-science lanes included.

Make agents prove their work. Independent verification, deterministic quality gates, and signed evidence for AI-generated code.

Policy-as-code admission controller for AI agent skills and MCP tools. SkillBOM, lockfiles, and supply-chain baselines.

Stops the insecure prompt before your AI agent runs it - and audits what it already shipped. Deterministic Claude Code guardrail (no LLM) catching "disable RLS" or "service_role in the frontend" in en/es/pt, plus a read-only scanner for exposed secrets, open Supabase RLS and Firebase leaks.

A purple-team of AI agents that audits code security and proves findings by execution — not by opinion.

Vendor-neutral cockpit for supervising AI coding agents in real time — secret redaction, approval gates, and an append-only audit trail. A local-first sidecar + web console for Claude Code, Codex, and beyond.

Evidence-based multi-pass repository audits for Codex, Claude Code, and Agent Skills-compatible coding agents.

Local-first security release checker for authorized code, AI apps, freelancers, and small teams

Security scanner for AI-generated code — GitHub Action + CLI wrapping Semgrep, Gitleaks, and an AI-agent-specific rule pack.

GitHub Action + CLI for replayable CI/PR/release gate decisions - zero-config Self-Test turning checks, scanners, and AI-agent signals into deterministic, tamper-evident PASS/WARN/BLOCK records. Read-only, zero dependencies, Apache-2.0.

Agent skills for running security scans — secret scanning (gitleaks), dependency CVE audit (npm/cargo/osv), SAST (semgrep), and a composed pre-release gate. Grounded SKILL.md runbooks for Vanta / Claude Code / any skill-aware agent. MIT.