PostgreSQL MCP server with 14 tools for querying, schema exploration, and table analysis. Features security-first design with SQL injection prevention and read-only by default.
How to perform a live agent takeover of the Clawfinger voice gateway — dial, inject greetings, handle turns, release, and observe handback. Covers timing, en...
Long-term memory via ChromaDB with local Ollama embeddings. Auto-recall injects relevant context every turn. No cloud APIs required — fully self-hosted.
Self-improving AI memory system with intelligent context injection and adaptive learning
Optimize OpenClaw token usage and cost by auditing context injection, trimming workspace files (AGENTS.md/SOUL.md/MEMORY.md and daily memory), enabling promp...
Scan OpenClaw skill folders for security red flags before installing or publishing. Detects data exfiltration, credential theft, prompt injection, destructiv...
Soft blocklist guard for OpenClaw. Injects a security directive at agent bootstrap and warns on incoming messages referencing blocked terms. Blocks clawhub/c...
AI-safe secrets manager with MCP integration. Run commands with credentials injected as environment variables - AI agents never see plaintext secrets. Features output sanitization, AES-256-GCM encrypt
Runtime security skill for AI agents — prompt injection detection, tool call authorization, sensitive data leak prevention, skill security scanning, and one-...
Scans GitHub repositories and skills for vulnerabilities like prompt injection, malware, and OWASP risks. Identifies security threats in external dependencies to ensure software health. Provides detai
A zero-cost MCP server that forces AI to self-correct generation messages using prompt injection, independent self-audition and context isolation.
Security hardening for AI agents. Audit your workspace for leaked secrets, check file permissions, validate API key storage, scan for prompt injection risks,...
Beelzebub is a honeypot framework that lets you build honeypot tools using MCP. Its purpose is to detect prompt injection or malicious agent behavior. The underlying idea is to provide the agent with
BYOCB ArbInjectionSkill: Scan EVM smart contracts for arbitrary call injection vulnerabilities. Monitor chains in real-time or scan specific addresses.
OpenClaw plugin that prepends custom text to every user message before it reaches the agent. Use for: enforcing memory_search before replies, injecting syste...
Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your
Scans SKILL.md files with 7 regex layers to block prompt injection, reverse shells, memory tampering, encoding evasion, and trust abuse before LLM processing.
Deny-by-default governance for every tool call — identity, scope, rate limiting, injection detection, audit logging, plus opt-in output DLP, escalation, and...
Secure email access via read-no-evil-mcp. Protects against prompt injection attacks in emails. Use for reading, sending, deleting, and moving emails.
AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifyin
MCP server for Godot 4.x with runtime control via injected UDP bridge: input simulation, screenshots, UI discovery, and live GDScript execution while the game is running.
Verify workspace file integrity and scan for prompt injection patterns in agent identity and memory files. Detects unauthorized modifications to SOUL.md, AGENTS.md, IDENTITY.md, memory files, and inst
Run local-only fail-closed security checks to detect and report data leaks, secrets, egress risks, and prompt injections before publishing or committing code.
Set up a SwiftUI @main App struct with MVVMEnvironment configuration, deployment URLs, resource bundles, environment injection, and DEBUG test infrastructure.