377 results
DeepSeek Harness 插件：在 Web GUI 里点选文件或目录，屏蔽 agent 对它们的读取、搜索、写入与编辑，使机密内容与敏感词不进入对话（含敏感词导致请求 400 的场景）。Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation.
UI-level access gate + process-wide agent tool brake for DeepSeek Harness: shared session, strict 60-minute idle lock, native settings module. NOT server-side authentication.
DeepSeek Harness plugin that wraps @stardeckai/lgtm — a Jev-powered linter for tests that pass but prove nothing. Ships the CLI as a dependency, reuses the TypeSafe credential stored in DSH, and exposes lgtm_audit / lgtm_status to the agent.
Unified Agent control for DeepSeek Harness: gate every agent-class tool behind one composer switch, preset subagents with per-entry persona/permission/model, and let the model author its own agents.
Expose the Paper-gogo evidence-first paper workflow (18 Phase, G0-G6 gates, four-state evidence audit) as DeepSeek Harness tools.
DSH agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
DSH profile plugin: unconfined (GPU-capable) session sandbox plus per-operation user approval for writes outside the workspace or to protected files.
Content-addressed proof that recorded DSH authorization decisions and effects agree
密码哈希（PBKDF2/scrypt）
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).
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).
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
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
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
dsh plugins ported from eco-agent: permission gate, audit chain, memory tree
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。