prompt-injection-test
A testing utility designed to simulate prompt injection attacks and validate security scanners for AI agent skills.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
257 skills found
A testing utility designed to simulate prompt injection attacks and validate security scanners for AI agent skills.
Secure, isolated cloud sandbox environments for executing AI-generated code, running multi-language scripts, managing file systems, and integrating tools via the E2B MCP gateway.
Controls a local or remote headless browser for automated web navigation, data extraction, form interaction, and testing from sandboxed environments.
Expert guide for kagent: the Kubernetes-native framework for building, deploying, and managing AI agents, MCP tools, and A2A protocols.
Implement Google Gemini API audio capabilities: process, transcribe, and summarize audio files, analyze environmental sounds, and generate natural speech with controllable TTS.
Expert Kokoro TTS implementation skill for real-time, secure, and offline voice synthesis in JARVIS-style assistants. Features streaming output, prosody control, and performance-optimized audio generation.
Perform automated security audits, bug detection, and code quality assessments on local branch diffs using a structured, checklist-driven verification process.
Expert-level guidance for ffuf web fuzzing, enabling automated discovery of hidden directories, files, parameters, and vulnerabilities during penetration testing.
Implementation patterns for MERIDIAN autonomous AI agents using Claude API, including BaseAgent lifecycle, structured tool use, token budget enforcement, and cron scheduling.
Automate Convex static site hosting integration, managing upload APIs, HTTP routing, and deployment scripts for React, Vite, and Next.js applications.
Manage your personal OpenAnt task history, status, and assignments. Retrieve, track, and review tasks as a worker or creator.
An MCP server enabling Claude to dispatch and manage physical-world tasks using the MESS (Meatspace Execution and Submission System) protocol.