dsh-mcpguard
by — · ChenLaoshiYF/dsh-mcpguard
★ 0 Stars
⑂ 0 Forks
Original language: English
About
Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, and credential leaks.
From the same category
by toby-bridges
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
★ 833
AGPL-3.0
Python
Sep 13, 2026
dsh plugin --profile web add dsh-api-relay-auditby sandbaseai
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
★ 643
↓ 8/wk
Apache-2.0
TypeScript
Sep 13, 2026
dsh plugin --profile web add managed-agentsby hashgraph-online
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
★ 602
Apache-2.0
Python
Sep 13, 2026
by xiaods
k8e.sh - OpenSource Agentic AI Sandbox Matrix
★ 489
↓ 18/wk
Apache-2.0
Go
Sep 13, 2026
dsh plugin --profile web add @k8e-sandbox/dsh-k8e-sandbox-bundleby howmp
面向 DeepSeek Harness（dsh）的渗透测试模式 @CloverSecLabs
★ 452
JavaScript
Sep 11, 2026
dsh plugin --profile web add @howmp/dsh-pentestby SeaOf0
基于dsh web实现的多种模式，目的是服务于redteam进行授权的安全研究，覆盖渗透测试、红队评估、代码审计等范围领域，请勿用于非法行为。（允许二开，赋予模块各位自己的业务逻辑，方法论只有自己熟练的才好用，好的方法论=好的生态）
★ 423
MIT
Python
Sep 11, 2026
dsh plugin --profile web add @dsh-external/dsh-redteam-model