接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
Enterprise-grade defensive input firewall for LLM autonomous agents. Inspects, filters, and neutralizes prompt injections, indirect jailbreaks, and instructions override exploits before passing untrusted text into prompts.
python mcp_server.py
sanitize_prompt: Analyze and cleanse text of malicious injection attacks.inspect_threats: Scan text and list identified security threat patterns.Strict heuristic and regex-based prompt injection and untrusted input guard detecting jailbreak markers, hidden instruction escapes, and indirect injection payloads
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Genpark Agent Prompt Guard Injection Sanitizer Skill 透過 stdio 在本機執行。
上次檢查時間:2026-10-27。 Strict heuristic and regex-based prompt injection and untrusted input guard detecting jailbreak markers, hidden instruction escapes, and indirect injection payloads