correctover
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
112 results
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
Read-only, offline-first security scanner plugin for DeepSeek Harness plugins.
First-run health check for DeepSeek Harness (dsh): verifies Node/pnpm/dsh toolchain, profile, API key, workspace and registry config, then prints actionable next steps. Zero runtime dependencies, read-only. CLI + agent-callable quickstart tool.
DeepSeek Harness plugin: injects an [IMPORTANT] chain-of-thought rule block at the very top of the system prompt of every model request (English CoT starting with I'm, no 'Let me', direct verbs).
DeepSeek Harness wallet plugin powered by the ChainGate TypeScript SDK.
V0 capability-disclosure scanner for DeepSeek Harness (DSH) cordis plugins: reports which sensitive services (credentials/shell/approval/sandbox/fs/tools...) a plugin declares or references before you trust it.
Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).
Look up what a DeepSeek Harness plugin can actually do, from inside dsh.
DSH Agent 上下文浸泡器:System Prompt 注入五维认知图鉴(宪法+速览常驻,全文技能化按需),末尾 HTML 注释快照提取链演化状态,历史快照滑窗保留与漂移自愈回路
DSH Web GUI: one-click expand/collapse all reasoning chains and tool chains in the current session (官方 repository-plugin 格式 / official bundle format)
Installation safety gate & data-protection guard for DeepSeek Harness: 60 static signature rules scan plugin sources for malicious install scripts, credential theft, obfuscation and network callbacks before 'dsh plugin add', with scan baselines (gate_diff), structured reports (gate_report), 12 destructive-command patterns and workspace-boundary checks.
DeepSeek Harness plugin: make the chain of thought open with "We need" instead of "Let me"
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
提示词工程模式:结构化推理(CoT/ToT)、few-shot、模板变量、生产级提示词优化。受 wshobson/agents(38k★ MIT)启发。
Policy-only multi-source quota router for DeepSeek Harness: deterministic task profiles, ordered candidate chains, health-aware fallback, and observable decisions.
DSH web_search provider with a runtime-editable search priority chain: zai-web-search / anthropic-web-search / openrouter-online dialects, settings-UI panel, no hidden fallback.
Offline content-addressed proof for supplied license-obligation delivery closure
DSH plugin that forces the agent's chain-of-thought and reasoning to stay in Chinese via a per-step system-prompt injection — 让 Agent 的思考过程也自动使用中文
Unified SSH remote-execution plugin for DeepSeek Harness — ProxyJump chain, SFTP filesystem, subprocess and PTY over ssh2
Offline content-addressed proof that independent builds reproduced byte-identical specified artifacts
Static trust audit for DeepSeek Harness plugins: capabilities, injected prompts, token cost, provenance, and a reproducible 0-100 trust score
Ordered, extensible web-search fallback chain for DeepSeek Harness.
Evidence-first inspection, compatibility verification, and quarantine tooling for DeepSeek Harness plugins.
Offline content-addressed proof that failed deployments converged to one last-known-good artifact