agent-security

Always-on compatibility testing for DeepSeek Harness plugins: exact releases, isolated runners, and fixable upstream issues.

X-ray for DeepSeek Harness plugins: declared capabilities vs actual behavior. Registry + static scanner + badges.

Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness.

Codex-style Auto Review inspired plugin for DeepSeek Harness, with native bridge and Linux sandbox integration

Agentic Control Plane for DeepSeek Harness — policy-check every tool call before it runs

Windows agent safety for DeepSeek Harness: preview risky calls, protect workspace boundaries, and explain audit decisions.

⚡ DROS™ VajraClaw for DSH: Deterministic Runtime Execution Governance & Security Circuit-Breaker Plugin

Governed platform access for DeepSeek Harness. Brokered credentials, owner-side approval, no API keys on the machine.

DSH / DeepSeek Harness plugin: runtime secret & PII redaction with mask, reversible vault and execution-time substitution

一个可直接链接到 DeepSeek Harness（DSH）Web profile 的独立安全检查插件。在安装或使用不受信任的 Skill 前，先执行浏览器本地粗检，再由用户决定是否调用 DSH 已配置的大模型进行结构化复核。

Ask what a DeepSeek Harness plugin can actually do, from inside your agent. Companion to dsh-xray.

Authentication and security hardening plugin for DeepSeek Harness

Offline-first security scanner for DeepSeek Harness plugins: prompt injection, ransomware, exfiltration, and supply-chain risks.

该仓库暂未提供项目说明。

Security guard plugin for DeepSeek Harness: secret redaction, a shell command denylist, prompt-injection scanning, and syntax verification.

Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin, gates privileged calls that follow untrusted content, and refuses credentials heading off the machine.