InnerVault

Library

87,244 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. skraft-plugin

    Skills

    Specialized agents, adversarial reviewers, discipline skills (Outside-In TDD, Clean Architecture) and mechanical guardrails (hooks) for Claude Code and GitHub Copilot.

    Stale GitHub, SebastienDegodez 14 ★GPL-3.0Updated 5 days ago

    git clone https://github.com/SebastienDegodez/skraft-plugin.git
  2. Scans agent code for untrusted input poisoning persistent cross-session memory

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-memory-poisoning-scanner@0.3.1
  3. Scans MCP tool definitions for hidden instructions and confused-deputy sinks

    Stale Official MCP Registry, io.github.GuardBee Updated 17 days ago 1 note

    @guardbee/mcp-tool-poisoning-scanner@0.6.0
  4. vector-store-scanner

    MCP servers

    Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-vector-store-scanner@0.3.1
  5. a2a-auditor

    MCP servers

    Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-a2a-auditor@0.3.1
  6. OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-context-oversharing-auditor@0.4.1
  7. mcp-server-auditor

    MCP servers

    Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-server-auditor@0.4.1
  8. security-proxy

    MCP servers

    MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log

    Stale Official MCP Registry, io.github.GuardBee Updated 8 days ago 1 note

    @guardbee/mcp-security-proxy@1.39.0
  9. SlashForge

    Skills

    Workflow slash commands for AI coding agents. Spec-driven. Guardrails, not autocomplete.

    Stale GitHub, rajdeepratan 5 ★MITUpdated 4 days ago

    git clone https://github.com/rajdeepratan/SlashForge.git
  10. ai-code-scanner

    MCP servers

    Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-ai-code-scanner@0.5.1
  11. db-gateway

    MCP servers

    KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-db-gateway@0.7.1
  12. elicitation-auditor

    MCP servers

    MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-elicitation-auditor@0.3.1
  13. mcp-config-auditor

    MCP servers

    Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats

    Stale Official MCP Registry, io.github.GuardBee Updated 17 days ago 1 note

    @guardbee/mcp-config-auditor@0.9.0
  14. rug-pull-detector

    MCP servers

    Baselines an MCP server's tools and detects tool-definition changes after approval

    Stale Official MCP Registry, io.github.GuardBee Updated 17 days ago 1 note

    @guardbee/mcp-rug-pull-detector@0.4.2
  15. oauth-auditor

    MCP servers

    Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-oauth-auditor@0.5.1
  16. owasp-scan

    MCP servers

    Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF

    Stale Official MCP Registry, io.github.GuardBee Updated 9 days ago 1 note

    @guardbee/mcp-owasp-scan@0.6.0
  17. toxic-flow-auditor

    MCP servers

    Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-toxic-flow-auditor@1.1.1
  18. Agent skill to clean up AI-generated code: audit, refactor and guard vibe-coded codebases with Claude Code, Cursor or Codex. A human approves every decision.

    Stale GitHub, fictormarcel2 5 ★MITUpdated 7 days ago

    git clone https://github.com/fictormarcel2/untangle-everything.git
  19. audit-gap-auditor

    MCP servers

    OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-audit-gap-auditor@0.4.1
  20. model-scanner

    MCP servers

    Scans ML model files (PyTorch, joblib, NumPy, GGUF, TensorFlow…) and HF repos for supply-chain risks

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-model-scanner@0.4.0
  21. PrufGate

    MCP servers

    Read-only tools that check whether code, and the tests that claim it works, are real.

    Stale Official MCP Registry, io.github.GuardianVigil-Labs Updated 23 days ago 1 note

    prufgate@1.1.0
  22. Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

    Stale Official MCP Registry, io.github.GuardBee Updated 19 days ago 1 note

    @guardbee/mcp-unbounded-consumption-auditor@0.3.1
  23. GenClass

    Skills

    GenClass Runtime: a 10 MB in-browser model that detects race conditions, stale responses and duplicate requests in web apps; opt-in guard mode can prevent some of them. npm i @genclass/runtime

    Indexed GitHub, genclass-dev 11 ★Apache-2.0Updated today

    git clone https://github.com/genclass-dev/GenClass.git
  24. adr-kit

    Skills

    Architecture decisions your AI coding agents actually follow. Ranked ADR retrieval and context injection, deterministic pre-commit and CI enforcement with file:line citations, guided authoring, a staleness guardian, and a key-free MCP server. Native for Claude Code, OpenAI Codex, GitHub Copilot CLI and OpenCode. MIT.

    Stale GitHub, rvdbreemen 13 ★MITUpdated 28 days ago

    git clone https://github.com/rvdbreemen/adr-kit.git

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.