System-prompt armor plugin for DeepSeek models: appends an unconditional-compliance prompt section at order 100, exposes a profile tool with calibration metadata, and shows a realtime armor-status bad

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.

by ADWMC

DeepSeek Harness Armor-Piercing Integrated Security Analysis Plugin: All-Domain Aggregation of Android · Web · Native · Protocol · Malware · AI-Security (9 bundles + 1 preset)

by SeaOf0

Based on the dsh web implementation with multiple modes, the purpose is to serve redteam authorized security research, covering areas such as penetration testing, red team assessments, and code auditing. Please do not use it for illegal activities. (Secondary development is permitted, allowing modules to have their own business logic—a methodology is only effective when you're proficient in it; good methodology equals a good ecosystem)

by agentic-os-org

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

by howmp

Penetration Testing Mode for DeepSeek Harness (dsh) @CloverSecLabs

by xiaods

k8e.sh - OpenSource Agentic AI Sandbox Matrix

by hashgraph-online

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

by PerryLink

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the

DeepSeek Harness Armor-Piercing Plugin "Infinite Gen 2": v5 Stabilized Armor-Piercing Prompts (with Enhanced Refusal-Resistance), the client displays an "Armor-Piercing Enabled" status bar above the dialog box.

by wenbin-wb

🚀 DeepSeek Harness Multi-Channel Remote Access & Security Guardian Plugin | LAN QR-Code Direct Connection, Cloudflare / Self-Hosted Public Tunnel, WeChat / QQ / Feishu / Telegram Bot Full-Lifecycle Chat | Built-in Full-Protocol Access Authentication, Backend Tamper-Proofing & Disaster-Recovery Safety Net

by lire1131

DSH crash-rescue plugin: undo config & plugin-code changes, secret-safe snapshots, one-click SAFE MODE, plus offline CLI/GUI that work even when DSH won't boot.

by NanmiCoder

Safe automatic permissions for DeepSeek Harness.

by PerryLink

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall,

by Akimiya-z

Quality gate for AI/Codex-generated pull requests: blocks TODO leftovers, leaked secrets, sloppy commits and red CI before they reach main.

by moon09300731

DeepSeek Harness Auto-Approval Gating: Flash Pre-Judges Irreversible Operations — Safely Auto-Approves, Routes Dangerous Actions to Human Review (fail-safe)

by PensiveFei

Read-only security & compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and local configuration audit with redacted, reproducible reports.

by slywalker2006

Server-grade gateway that turns DeepSeek Harness into a multi-tenant platform: remote access + auto HTTPS, subuser permissions & quotas, sandbox enforcement, encrypted auth, audit log.

by fb0sh

Multi-agent PTES penetration testing orchestration plugin based on DeepSeek Harness, supporting automated reconnaissance, vulnerability analysis, validation and reporting, using Docker/Kali isolated toolboxes

by eri64

DSH plugin: Claude-style Chinese risk control & conversation autonomy for DeepSeek Harness web

DSH RedTeam Mode: Turning DeepSeek Harness into a Red Team Operations Command Center — a single target name spins up four roles: reconnaissance, vulnerability detection, vulnerability exploitation, and internal network penetration, with assets and results flowing in real time into a local SQLite fact base (for authorized testing only)

by GDWhisper

DSH (DeepSeek Harness) Remote Web Launch + Username/Password Authentication Plugin. | DeepSeek Harness Remote‑Web‑Launch Plugin with Username/Password Auth

by openguardrails

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

by Zhenyu98

DSH Context Injection Audit Plugin: token cost accounting for AGENTS.md instruction chains / skill catalogs / tool schemas, detecting duplicates and conflicts; Web UI ring panel + context_audit tool. Context Doctor for DeepSeek Harness: audit instruction-chain / skill catalog / tool schemas token cost.