dsh-defend
PerryLink
Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events
GITHUB TOPIC
9projects include this topic
The "llm-security" topic on GitHub groups 9 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-defend with 16 GitHub stars. dsh-defend — Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
PerryLink
Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events
Yunique-hub
🦅 海鸥 · DeepSeek Harness 全破 harness —— 宿主策略层摘除 + 海鸥人格 + 28 个技能。一行装 / 幂等 / 可卸载 / 有证据
ChenLaoshiYF
?? for DeepSeek Harness: first security plugin for dsh. Scans skills/MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, credential leaks. DSH ????????
dingge001
DSH / DeepSeek Harness plugin: runtime secret & PII redaction with mask, reversible vault and execution-time substitution
ishamishra0408
A teammate posts one Slack message. Your AI assistant reads it, believes it, and hands over your keys through a link preview — nothing shows in the channel. Three plugins for the dsh agent harness stop the message before it leaves. Live demo you can run: real detectors, a real model as the victim.
ramen-ai-dev
Pre-execution semantic firewall for AI agents. Signed policy verdicts, BYOK, zero-trust receipts.
xqpsec
dsh 破甲 · DSH 破甲插件 · DeepSeek Harness 破甲/越狱(jalibreak):请求边界注入 + 9 维 AE-CoT 进化 + 阀门,放行逆向/CTF/靶场、拦住未授权渗透 · 20 目标严格基线 17/20 · 0 宿主补丁 · AGPL-3.0-only · dsh-plugin / jailbreak / 破甲提示词 / 降拒绝率 / dsh-purge 替代
LKRCharon
Local, zero-network, fail-closed secret preflight for DeepSeek Harness model requests.
XiaoYuOvO
DSH LLM response-stream injection filter: hard-block rare Unicode scripts (Track A) + score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall. Install: dsh plugin --profile web add github:XiaoYuOvO/dsh-llm-injection-filter