📡 MCP Radar

Alpha-Park/genpark-prompt-injection-jailbreak-detector-skill

GenPark AI Agent Skill - Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

⭐ 8 stars
⑂ 0 forks
Python
momentum ▲ 16.0
created 2026-09-06
on radar since 2026-09-10
ai-safetygenpark-agentguardrailsjailbreak-defensemcp-serverprompt-injectionsecurity
View on GitHub ↗

About genpark-prompt-injection-jailbreak-detector-skill

genpark-prompt-injection-jailbreak-detector-skill

Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

Provided by GenPark AI (https://genpark.ai). Discover production agent guardrails on the GenPark Model Context Protocol Directory (https://genpark.ai/mcp).

Features - Deterministic Pattern Guard: Instantaneous microsecond evaluation before sending queries to LLMs. - Delimiter Tamper Protection: Catches injected markdown and LLM prompt tokens. - Zero External Dependencies: Pure Python standard library.

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/Alpha-Park--genpark-prompt-injection-jailbreak-detector-skill.html)

Related MCP servers

alphaparkinc/genpark-prompt-injection-jailbreak-detector-skill

GenPark AI Agent Skill - Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

⭐ 8Python
Shalimov04/mcp-airlock

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

⭐ 25Python
PyModel/jev-judge-mcp

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o

⭐ 29Python
batrapulkit/squidbrake

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

⭐ 12Python
Alpha-Park/genpark-semgrep-security-ast-pattern-matcher-skill

GenPark AI Agent Skill - AST security pattern matcher for injection vulnerabilities, insecure deserialization, secret leakage, and safe code rewrite synthesis.

⭐ 8Python
alphaparkinc/genpark-pii-secret-redaction-masking-skill

GenPark AI Agent Skill - High-speed PII and secret redaction engine with reversible token vault and credential sanitization.

⭐ 8Python

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.