TOPY.AI · AI CSO
Founders' AI CSO: vulnerabilities, dependencies, secrets, verified-site checks, threat model, fixes.
やりたいことや使っているアプリで検索し、カテゴリで絞り込めます。
利用スコア順:GitHubスター、週あたりのダウンロード数、最近のリリース、エンドポイントの応答。よく使われている=一番良い、ではありません。
カードの見方:↓ 週あたりのダウンロードi★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Founders' AI CSO: vulnerabilities, dependencies, secrets, verified-site checks, threat model, fixes.
What changed in your stack since the model's cutoff, error fixes, and security-scanned skills/MCPs
Find and redact leaked secrets, wallet keys and PII before an AI agent sends text.
One-time, end-to-end encrypted secrets for agents. 0.005 USDC per secret via x402.
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Security audits for WordPress plugins and themes — 62 verification layers, fix plans and SBOMs.
AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
An MCP server that provides interaction with StackHawk's security scanning platform.
Detect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.
Electron.js MCP server — IPC scaffolding, security auditing, build tooling for AI assistants
The deterministic attack-surface perception layer for AI security agents
Maltego OSINT for AI agents: transforms, Machines, link-graph analysis and native .mtgx.
Encrypted secrets vault for AI agents. 27 MCP tools resolve secrets at runtime, never leaking them.
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
Run scoped, authorized Sn1per pentest, recon and attack surface scans from AI agents; read findings.
Run Sherlock, Maigret, Holehe, GHunt, theHarvester, SpiderFoot and more OSINT tools locally
AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints
Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.
Local-first supply-chain security gate for npm/pnpm/bun: typosquat, release age, provenance checks
AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.
Credential isolation for AI agents. Inject secrets at the network boundary.