Skarn
Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted
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
Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted
Read-only Keeper MSP posture across every client, with history, a change feed and no path to a
Kolivri AI Voice MCP Server — real phone line for AI agents with KYC & rate-limit guards.
Security layer for AI agents: Retrieve for controlled SQL reads, Guard for allow/deny writes.
RAM-only HTTP debugging proxy and MCP server in Go. AI agents see salted tags, never secrets.
Site/email/agent safety and monitors: SPF/DKIM, SEO, change + RSS monitors, hidden-AI, WHOIS (7).
Security checks for apps built with AI tools: scan a GitHub repo and read the fix prompts.
Scan a URL before your agent reads it: hidden prompt injection, phishing, clean markdown.
Check URLs, indicators and CVEs against threat intelligence before you act on them.
Request and send secrets for AI agents, end-to-end encrypted and never shown in the chat.
Read-only access to Harbor: projects, artifacts, vulnerabilities, robots, replication, agent skills.
Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.
Local checks for Unicode confusables, mixed scripts, invisible controls, and suspicious identifiers.
Exploit Prediction Scoring System scores: how likely a CVE will be exploited in the next 30 days.
Offline static analysis of n8n workflow exports: dead ends, cycles, missing triggers, secrets.
Honeypot threat intel: IOCs, sample comparisons, evidence clusters and ThreatDrop case status.
Offline security-artifact analysis: endpoint and secret mining, IDOR diffs, JWT triage
Reference MCP server for synthetic APC action-security evaluation and local SQLite sandbox testin...
Search agent skills ranked by GitHub stars, with growth, security signals and pinned installs.
Read-only Petra Security MCP: M365 compromise incidents, failed attacks, posture, tenants, usage.
LLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.