Library
87,244 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
skraft-plugin
SkillsSpecialized agents, adversarial reviewers, discipline skills (Outside-In TDD, Clean Architecture) and mechanical guardrails (hooks) for Claude Code and GitHub Copilot.
git clone https://github.com/SebastienDegodez/skraft-plugin.git -
memory-poisoning-scanner
MCP serversScans agent code for untrusted input poisoning persistent cross-session memory
@guardbee/mcp-memory-poisoning-scanner@0.3.1 -
tool-poisoning-scanner
MCP serversScans MCP tool definitions for hidden instructions and confused-deputy sinks
@guardbee/mcp-tool-poisoning-scanner@0.6.0 -
vector-store-scanner
MCP serversProbes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
@guardbee/mcp-vector-store-scanner@0.3.1 -
a2a-auditor
MCP serversScans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
@guardbee/mcp-a2a-auditor@0.3.1 -
context-oversharing-auditor
MCP serversOWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks
@guardbee/mcp-context-oversharing-auditor@0.4.1 -
mcp-server-auditor
MCP serversScans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
@guardbee/mcp-server-auditor@0.4.1 -
security-proxy
MCP serversMCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
@guardbee/mcp-security-proxy@1.39.0 -
SlashForge
SkillsWorkflow slash commands for AI coding agents. Spec-driven. Guardrails, not autocomplete.
git clone https://github.com/rajdeepratan/SlashForge.git -
ai-code-scanner
MCP serversScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
@guardbee/mcp-ai-code-scanner@0.5.1 -
db-gateway
MCP serversKVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log
@guardbee/mcp-db-gateway@0.7.1 -
elicitation-auditor
MCP serversMCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs
@guardbee/mcp-elicitation-auditor@0.3.1 -
mcp-config-auditor
MCP serversScans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
@guardbee/mcp-config-auditor@0.9.0 -
rug-pull-detector
MCP serversBaselines an MCP server's tools and detects tool-definition changes after approval
@guardbee/mcp-rug-pull-detector@0.4.2 -
oauth-auditor
MCP serversScans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
@guardbee/mcp-oauth-auditor@0.5.1 -
owasp-scan
MCP serversUnified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF
@guardbee/mcp-owasp-scan@0.6.0 -
toxic-flow-auditor
MCP serversFinds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
@guardbee/mcp-toxic-flow-auditor@1.1.1 -
untangle-everything
SkillsAgent 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.
git clone https://github.com/fictormarcel2/untangle-everything.git -
audit-gap-auditor
MCP serversOWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit
@guardbee/mcp-audit-gap-auditor@0.4.1 -
model-scanner
MCP serversScans ML model files (PyTorch, joblib, NumPy, GGUF, TensorFlow…) and HF repos for supply-chain risks
@guardbee/mcp-model-scanner@0.4.0 -
PrufGate
MCP serversRead-only tools that check whether code, and the tests that claim it works, are real.
prufgate@1.1.0 -
unbounded-consumption-auditor
MCP serversScans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)
@guardbee/mcp-unbounded-consumption-auditor@0.3.1 -
GenClass
SkillsGenClass 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
git clone https://github.com/genclass-dev/GenClass.git -
adr-kit
SkillsArchitecture 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.
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.