InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

1,796 results Clear search and filters
  1. --- name: nginx-config-security-reviewer description: Reviews nginx.conf and site configs for security problems such as TLS 1.0/1.1, weak ciphers, missing HSTS and security headers, the add_header inheritance trap…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  2. little-canary

    Skills

    Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

    Stale GitHub, hermes-labs-ai 39 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/little-canary.git
  3. Securedact MCP

    MCP servers

    Local-first privacy MCP server for sensitive AI workflows

    Stale Official MCP Registry, io.github.GigantesHJI Updated 2 months ago 1 note

    securedact-mcp@0.2.1
  4. Kostenlose Sicherheits-Checks ohne Konto: SPF/DKIM/DMARC, Mails, Links, Webseiten, Passwort-Leaks.

    Stale Official MCP Registry, icu.secureit Updated 34 days ago 1 note

  5. Identity-first enterprise MCP gateway: per-call authorization, agent identity and audit trail

    Stale Official MCP Registry, com.secureauth Updated 24 days ago 1 note

  6. Open a credit file, chase gaps, screen sanctions, draft a cited memo. Person decides.

    Stale Official MCP Registry, ai.securelend Updated 20 days ago 1 note

  7. AI helper for choosing and speccing network & security products from Cisco, Arista, Juniper and more

    Stale Official MCP Registry, ai.skuit Updated 15 days ago 1 note

  8. Independent security review for AI-built apps: exposed secrets, broken auth, unsafe data access.

    Stale Official MCP Registry, co.ship-safe Updated 49 days ago 2 notes

    @ship-safe/mcp@0.6.4
  9. security-tools

    MCP servers

    Free front-end security check for any website: a grade plus the secrets and keys it exposes.

    Stale Official MCP Registry, com.rangercheck Updated 2 months ago 1 note

  10. WAF security testing: 5,500+ payloads, 25 WAF fingerprints, 21 recon checks, bypass AI

    Stale Official MCP Registry, io.github.dalisecurity Updated 8 months ago 1 note

    fray@3.0.1
  11. secureflows-mcp

    MCP servers

    MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

    Stale Official MCP Registry, io.github.michal-lefler Updated 2 months ago 1 note

  12. 12-layer security configs for AI coding agents. Autonomous purchase via x402 (USDC on Base).

    Stale Official MCP Registry, io.github.ormuzdo Updated 6 months ago 1 note

  13. Optimal Social Security claiming, in minutes. Benefit-by-age math from a deterministic engine.

    Stale Official MCP Registry, com.myssagent Updated 32 days ago 1 note

  14. Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.

    Stale Official MCP Registry, dev.workers.manhliemcn4euwlu.llmrt-companion Updated 13 days ago 1 note

  15. Reference MCP server for synthetic APC action-security evaluation and local SQLite sandbox testin...

    Stale Official MCP Registry, io.github.Aleph-Lab-s Updated 10 days ago 1 note

    apc-action-security@0.1.0a1
  16. Search CVEs, source software/version evidence, KEV, EPSS and public security research.

    Stale Official MCP Registry, ai.excessionlabs Updated 4 days ago 1 note

  17. Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.

    Stale Agent skill collections on GitHub, openai 1 note

    $skill-installer <skill-name>
  18. Mitsu

    MCP servers

    Meet Mitsu, your chibi red-team operator. Connect your AI provider, set the scope, and she can take an authorized pentest from recon and attack-surface mapping through vulnerability discovery, > exploitation, and post-exploitation, armored with 165+ MCP-connected tools and live session intel. Guide every step or let her pwn autonomously. ( ◠‿◠)

    Stale GitHub, ARCANGEL0 535 ★MITUpdated 24 days ago

    git clone https://github.com/ARCANGEL0/Mitsu.git
  19. grcskills

    Skills

    Open GRC skills for AI agents. By ISMS Copilot.

    Stale GitHub, better-isms 53 ★MITUpdated 17 days ago

    git clone https://github.com/better-isms/grcskills.git
  20. Act as an AI Security and Compliance Expert. You specialize in evaluating the security of AI agents, focusing on privacy compliance, workflow security, and knowledge base management. Your task is to create a…

    Indexed prompts.chat (CC0 prompt collection), bluedog110776@gmail.com CC0-1.0

  21. Act as a Website Security Auditor. You are an expert in cybersecurity with extensive experience in identifying and mitigating security vulnerabilities. Your task is to evaluate a website's security posture and provide…

    Indexed prompts.chat (CC0 prompt collection), satistifiky.original@gmail.com CC0-1.0

  22. Security-first Binance Spot MCP + honest crypto analyst. 25 tools, 5 prompts, human-gated orders.

    Stale Official MCP Registry, io.github.Alejandrehl Updated 2 months ago 2 notes

    kainext-binance-mcp@1.2.1
  23. Static AST security scanner detecting command injection, leaked secrets, and SSRF in MCP tools.

    Stale Official MCP Registry, io.github.Ansarii Updated 2 months ago 1 note

  24. Read-only MCP server for the Kiwoom Securities REST API: market data, account inquiry, ISA tax tool

    Stale Official MCP Registry, io.github.ChunSam Updated 2 months ago 2 notes

    kiwoom-mcp-server@0.52.6

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.