Плагины

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

Сканирует навыки и конфигурации MCP на предмет prompt injection, омоглифов, скрытого Unicode, опасных shell-команд и утечек учётных данных.

Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets