跳到主要内容

prompt-injection 11

  • dsh-secure-audit v0.2.11 已验证 85

    Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible

    dsh plugin add dsh-secure-audit
  • dsh-defend v0.3.21 已验证 23

    Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets

    dsh plugin add dsh-defend
  • dsh-jev-tools v0.1.13 已验证 Web 界面 12

    Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

    dsh plugin add dsh-jev-tools
  • deepseekeyes v0.8.2 已验证 Web 界面 7

    Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

    dsh plugin add @dttxorg/deepseekeyes
  • dsh-subagent-default-model v2.1.4 已验证 Web 界面 5

    为 DeepSeek Harness 子代理配置默认模型:多模型顺序/随机分配、跨供应商连接失败故障转移,并在轨迹/对话视图显示当前供应商与模型,同时以一行真实提示词把当前路由注入子代理上下文。

    dsh plugin add dsh-subagent-default-model
  • dsh-fact-check v1.3.0 已验证 1

    Fact-checking skill for DeepSeek Harness: verifies claims against the open web instead of model memory, cross-checks independent sources across domestic and international search ecosystems, and can route three factual judgements (does the evidence support

    dsh plugin add dsh-fact-check
  • dsh-round-inject v0.1.28 已验证 Web 界面

    Periodic prompt injection for the DeepSeek Harness Web GUI: every N model invocations (conversation turns and tool-call steps both count) the plugin injects a user-configured prompt as a model-visible user message; the first injection happens at conversat

    dsh plugin add dsh-round-inject
  • dsh-jev-guardrails v0.1.1 已验证

    DeepSeek Harness plugin: Jev-backed guardrails for prompts, tool calls, tool results, and model responses.

    dsh plugin add @codebam/dsh-jev-guardrails
  • dsh-model-safety-gate v0.3.1 已验证 Web 界面

    Independent two-layer safety gate around the DeepSeek Harness agent loop: deterministic and model-classifier verdicts for prompts, streamed output, tools, and tool results

    dsh plugin add @yadsh/dsh-model-safety-gate
  • dsh-prompt-firewall v0.2.5 已验证 Web 界面

    Prompt hygiene, observability, and policy middleware for DeepSeek Harness

    dsh plugin add @yadsh/dsh-prompt-firewall
  • dsh-correctover v1.0.3 已验证

    Correctover runtime security for DeepSeek Harness (DSH): CCS 7-dimension verification, command-injection/SSRF/credential-exfil blocking, Ed25519 receipts, audit-first. Install with `dsh plugin add dsh-correctover`.

    dsh plugin add dsh-correctover