Sécurité et permissions

Governed platform access for DeepSeek Harness — no credential on the machine

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

Enterprise compliance for DeepSeek Harness — SOC2/GDPR automated checks, sensitive-info redaction, and a redacted tool audit trail. · DSH 企业级合规插件：SOC2/GDPR 自动化合规自检、敏感信息拦截与脱敏、操作日志审计追溯。

Hold a DeepSeek Harness agent to a capmark capability manifest: mask its tools and judge every call.

Honesty guardrails on the tool pipeline: blocks a coding agent from weakening tests, swallowing errors, stubbing type checks, or deleting tests through the shell — nine deterministic hooks, each backed by a planted-failure test proving the guard can fail.

Lifecycle supervision, evidence-driven audit subagents, safe intervention, and blind acceptance gates for DeepSeek Harness

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

Pre-execution guardrail: vetoes dangerous shell commands and blocks secret/credential leaks before they run.

Auto-reject unanswered permission requests with a model-visible timeout notice

Egress policy for DeepSeek Harness: a host allowlist on web_fetch and web_search enforced at connect time, audit-mode by default, with OCSF Network Activity records

Codex-inspired managed approval for DeepSeek Harness: risk-based MCP review, one-time grants, explicit denials, and human fallback on reviewer failure.

Silence Chrome/iCloud password-manager prompts over DeepSeek Harness API-key inputs: rewrites password-type secret fields into masked text fields so browser password managers never treat DSH API keys as account passwords.

文件改动确认机制（双面插件）：write/edit/str_replace_editor 写入前弹出确认条，内嵌 GitHub 风格 diff（行号 + 红删绿增），允许本次 / 拒绝。File-change confirmation with inline diff for DeepSeek Harness.

Read-side SIEM forwarder for DeepSeek Harness: normalises session activity to OCSF and ships it

Data-loss-prevention plugin for DeepSeek Harness: a non-configurable tool guard floor, tool-result redaction, and fail-closed telemetry redaction

DSH 多租户账户与授权插件：PostgreSQL 存储 + admin 管理 API + 每账户独立工作目录（独立插件，不改 DSH 核心）

Password gate for dsh-web: opening the web port requires a username/password login; account credentials are stored salted+scrypt-hashed and AES-256-GCM encrypted in a local config file under $DSH_HOME. Host-only cordis plugin, no dsh source changes.

Password + CIDR gate for DeepSeek Harness web / DeepSeek Harness 局域网密码门禁

HashiCorp Vault backend for the credential seam: KV v2/v1, AppRole machine auth, per-operation reads so rotation needs no restart, and compare-and-swap writes.

Container-isolated backend for the `ctx.codeRuntime` seam: each Code Mode program runs in a fresh container with no network, a read-only rootfs, dropped capabilities, and kernel-enforced memory, CPU and pid ceilings.

Zero-interruption audit and fuse blocking for DeepSeek Harness: silently records every tool call with deterministic risk scoring, cumulative-risk bonuses, risk-level breakdowns and retention-based cleanup; blocks irreversible catastrophes (protected-path deletion, disk wipe, force-push to protected branches/refs, credential exfiltration), and renders a redacted /risk-guard operation bill with --since filtering.

Plugin value auditor: pre-install review (source scan + LLM judge) and post-install audit of installed bundles, with model-switch re-audit reminders.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Agent governance suite: policy-based tool gating (allow/deny/ask with wildcards and priorities), a structured JSONL audit trail, and per-agent token quotas against the host token meter, with state under $DSH_HOME/gov.