Search
aicordon
Mikhail Gribov <[email protected]>
Local prompt-injection scanner for untrusted text: 100-200 documents/s on one CPU core, one false alarm per thousand, no model
...moreaisona-skill-guard
aisona-lab <[email protected]>
Audit Agent Skills and packages before they touch your machine. Deterministic checks. Exit codes. No vibes.
@guardbee/mcp-ai-code-scanner
guardbee.ai
MCP server that scans code for insecure LLM/AI integration patterns — client-exposed API keys, unsafe handling of model output, excessive agent tool permissions, and PII sent to third-party LLMs
...more@elizaos/plugin-suno
shawticus
Suno AI music generation plugin for ElizaOS - Enables AI-powered music creation and audio manipulation
promptsafe
PromptSafe Contributors
Lightweight AI prompt injection and system prompt leakage shield for LLM apps. Zero dependencies, works offline.
agent-redteam
uninhibited-scholar
AI Agent 红队安全测试平台 — 从 CLI 到 Dashboard
@guardbee/mcp-llm-redteam
GuardBee
MCP server that red-teams a live LLM endpoint or chatbot with canary-based jailbreak/extraction/obfuscation probes to test whether known bypass techniques defeat its guardrails
...moreavanasec
leprofcode
A robust, production-ready CLI tool for detecting secrets and credentials in your codebase
@guardbee/mcp-config-auditor
guardbee.ai
MCP server that audits installed MCP client configs (Cursor, Claude Desktop, Windsurf, VS Code) for unpinned packages, secrets in env/args, wildcard auto-approve, unauthenticated remote endpoints, typosquats, and cross-server tool shadowing
...morefinagent-redrange
Emmanuel Guilherme Junior
A reproducible, defensive red-team range for financial-services AI agents.
blackduck-polaris-mcp-server
easygoingcoder
Feature-rich MCP server for Black Duck Polaris — trigger SAST/SCA/DAST scans, query findings, generate reports (SBOM, SPDX, CycloneDX), manage policies, triage issues, and more. Works with Claude Code, Claude Desktop, GitHub Copilot, Cursor, and any MCP-c
...more@guardbee/mcp-tool-poisoning-scanner
guardbee.ai
MCP server that scans other MCP servers' tool definitions for tool poisoning (hidden instructions embedded in a tool's description, read as trusted context by the calling LLM) and confused-deputy mismatches (a tool's name/description promises read-only be
...moremcp-install-guard
oplooins
Scan MCP servers before installing them
toan203/osv-ui
[](https://glama.ai/mcp/servers/toan203/osv-ui) 📇 🏠 🍎 🪟 🐧 - Visual CVE audit dashboard for npm, Python, Go, and Rust. Scan from Claude/Cursor, opens a browser UI for human review (human-in-the-loop), applies fixes with explicit confirmation. Powered by OSV.dev.
...moreAi Skills
sanjay3290
Collection of agent skills for AI coding assistants
projectair
Vindicara <[email protected]>
Project AIR: forensic reconstruction and incident response for AI agents. Turn agent traces into signed forensic records with BLAKE3 + Ed25519.
...moremodality-mcp-kit
hillliu
Modality MCP Kit - Schema conversion utilities for MCP tool development with multi-library support
mcp-api-pentest
Jose Nieto <[email protected]>
MCP server for autonomous API logic penetration testing — OWASP API Top 10 / BOLA-IDOR detection via LLM-driven analysis
Reticle
soth-ai
Reticle intercepts, visualizes, and profiles JSON-RPC traffic between your LLM and MCP servers in real-time, with zero latency overhead. Stop debugging blind. Start seeing everything.
...moreToolhive Registry Server
stacklok
An API server that implements the official MCP Registry API, providing standardised access to MCP servers from multiple backends, including file-based and other API-compliant registries.
...more