Search
solomon-ai-firewall
Enterprise-grade LLM security guardrail library — 100+ Active Guards, LLM Traffic Monitor, 509 tests, zero core dependencies. Protects against prompt injection, data leakage, PII exposure, tool poisoning, goal hijacking, and supply chain attacks.
...moreblitzstrike
shinthink
Blitz Strike — a universal MCP security-audit toolbelt. BLITZ sweeps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE verifies live. 57 attack chains, 130-tool catalog, intelligence data layer. One server, every agent.
...moreduriantaco/skylos
duriantaco
[glama](https://glama.ai/mcp/servers/@duriantaco/mcp-skylos) 🐍 🏠 🍎 🪟 🐧 - Dead code detection, security scanning, and code quality analysis for Python, TypeScript, and Go. 98% recall with fewer false positives than Vulture. Includes AI-powered remediation.
...moreTopgent
farikonsec
Monitor your local AI agents. See what files they can reach, what networks they communicate with, and stop them if required. Detect a rogue agent.
...moreDawnforge Pentest
xiabai2008
Multi-agent AI penetration testing workbench. Evidence-enforced anti-hallucination, agent-agnostic (Claude/Codex/OpenCode/Cline/Trae), continuously growing memory.
...moreClaude BugHunter
elementalsouls
A Claude Code skill bundle for bug hunting and external red-team work - 51 skills, 15 slash commands, 574+ disclosed-report patterns curated across 24 vulnerability classes, plus enterprise identity + infrastructure attack matrices.
...moreprompt-protection
mughalhere
Detect and strip malicious prompt injection, jailbreaking, and data exfiltration attempts from LLM inputs. Zero dependencies. Works in Node.js and browsers.
...moreopensentry
sharma
Tiered prompt-injection validation layer. Zero-dep sub-ms Tier 0 core (Node + edge identical), optional local ML + remote guard tiers.
...moresechelix
Omar Mohamed Helal
Optional execution runtime for the SecHelix AppSec Agent Skill: deterministic reasoner DAG, budget governor, coverage ledger and replayable evidence.
...moreopensentry
sharma
Tiered prompt-injection validation layer. Zero-dep sub-ms Tier 0 core (Node + edge identical), optional local ML + remote guard tiers.
...morecreate-security-txt
dreamseer
Create an RFC 9116 compliant security.txt file.
acidtest
currentlywebsite
Security scanner for AI agent skills. Scan before you install.
mcp-audit-scanner
Adam Dudley <[email protected]>
Privacy-first security scanner for MCP server configurations
rn-secure-keystore
tksreact
A comprehensive, cross-platform React Native wrapper for secure key-value storage using native security features of Android and iOS. It supports **biometric authentication**, **hardware-backed encryption**, and deep platform integrations such as **Android
...morePulsarAI
"Sina (sinamsv)" <[email protected]>
Security library for AI applications: guards against prompt injection and unsafe tool calls.
cordova-talsec-plugin-freerasp
GitHub Actions
Cordova plugin for improving app security and threat monitoring on Android and iOS mobile devices.
Ai Code Security
ai-code-security
Security framework for AI-generated code. Prompts, checklists, and tools for Cursor, Claude, and Copilot.
@itsmatteomanf/astro-security-txt
itsmatteomanf
Generate a security.txt file for your Astro site
agentsec-ai
Security scanner for AI agents and MCP servers. OWASP Agentic Top 10 mapping, SARIF output, CI/CD ready.
Deep Security Check
give-jd
Defensive, read-only security assessment skill for Claude Code (Semgrep + osv-scanner + gitleaks) with a reproducible reliability grade (0-100, A-F).
...more