407 results
DSH plugin: a codex-style apply_patch tool (*** Begin Patch / *** Update File / *** Add File / *** Delete File) injected into the model toolset through DSH's built-in sandbox, with a settings card to choose injection scope (off / GPT models only / all models).
Pre-write reuse firewall for DeepSeek Harness: before the agent writes a new helper/service, surface the existing implementations that already cover that intent. Deterministic retrieval (no LLM) backed by the Auto_code_audit capability channel.
Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.
Offline-first static admission scanner for DeepSeek Harness plugins.
Session management for DeepSeek Harness (DSH): list all historical sessions in a settings page and physically delete a session's log directory (with a type-to-confirm dialog and an audit trail).
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.
Standalone DeepSeek Harness access-mode plugin with Default, No Edit, and Auto modes
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
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.
Governed platform access for DeepSeek Harness — no credential on the machine
Look up what a DeepSeek Harness plugin can actually do, from inside dsh.
DeepSeek Harness 密钥保险库插件：密钥自动脱敏、自动收纳、密码本设置页、跨重启持久（官方 profile bundle）
记忆审计技能:对 AI agent 的记忆文件(MEMORY.md/LESSONS.jsonl/规则库)做静态体检,扫出越界宣称(已达 AGI/最强/100% 成功)、无证据完成声明、重复条款;报告是候选不是判决,每条带行号与原文供人工复核。适用:审计自己或他人的 agent 记忆、季度记忆体检、向团队展示记忆质量时。
Offline content-addressed proof for supplied license-obligation delivery closure
Approval guard for DeepSeek Harness: write/edit/editor/bash calls touching sensitive paths (.env, .git, SSH keys, .pem) and reads of SSH keys or certificates become an approval ask.
Offline content-addressed proof for supplied vulnerability-remediation closure
DeepSeek Harness plugin: a citable append-only JSONL of filesystem touches — path, op, sha256 before and after — carrying no file contents
Harness 事件流审计面板：观察事件类型、分发模式、计数与最近事件，帮助插件作者理解 harness 内部发生了什么
Secret & dangerous-pattern scanner for DeepSeek Harness — a security_scan tool that finds leaked API keys, tokens, private keys and credential files, with full redaction.
Structured code review skill for DeepSeek Harness -- bugs, security, performance, style
Press Enter to approve the sandbox permission-escalation prompt in the DeepSeek Harness WebUI instead of clicking the Allow once button.
DeepSeek Harness plugin: predict (pre-install) and detect (post-install) duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services to prevent Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".
Login wall and public gateway for DeepSeek Harness cloud deploys.