prompt-injection

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

Security-audit skill pack + plugin_vet supply-chain gate for DeepSeek Harness (dsh): 8 bilingual agent skills (secret scan, dependency audit, supply-chain review, prompt-injection review, audit orchestration, threat modeling, vuln intel, incident response) plus the plugin_vet automated pre-install scanner. Apache-2.0.

Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.

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

?? for DeepSeek Harness: first security plugin for dsh. Scans skills/MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, credential leaks. DSH ????????

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

dsh 全局防提示注入/上下文病毒感染插件：扫描工具参数、结果、进模型前消息与出站流；quarantine/block/monitor 三模式 + 金丝雀 + 可演进签名库（学习/导入/导出）。纯 JS 零原生依赖。

Private, per-project prompt rules for DeepSeek Harness — matched by git remote/repo/path, worktree-aware, never committed to the repo

Task-to-skill pairing for DeepSeek Harness — pours the minimal set (usually one; zero when plain tools suffice), prefers workflow skills over hand-composed atomics. Laziness ladder, quarantine → SkillSpector scan → explicit human approval, never auto-installs. 任务配技能 · 懒惰阶梯 · 安全酒窖 · 绝不自动安装

DSH plugin for agent observability and security evaluation

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。

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

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.