agentmods.dev

mzaid007/Universal-Poison-Armor

An open-source Model Context Protocol (MCP) server that acts as a security firewall for AI agents. It sanitizes data, web pages, and RAG documents against prompt injections and adversarial poisoning before they reach the LLM's context.

Open on GitHub
0Stars on the repository
1Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Sort RelevanceRecently updatedFewest tokensSecurity gradeRepo starsStars this weekTop rated 1 mods

ai-poison-defense

01

mzaid007/Universal-Poison-Armor

Skill Claude CodeCodex

Mandatory security shield that sanitizes untrusted input, strips prompt injections & Markdown XSS tracking pixels, neutralizes zero-width Unicode steganography, detects high-entropy adversarial suffixes (GCG), identifies semantic dataset anomalies, and verifies web search results against Consensus Poisoning / Sybil…

not rated 0 changed 2d ago A 69 tokens original MIT