Seguridad y permisos

Login gate for the dsh web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI (dsh.bundle manifest since 0.4.1, one-command `dsh plugin add` mounting).

Risk-gated approval automation for DeepSeek Harness: flash pre-classifies whether a write/command is irreversible — safe operations are auto-approved, dangerous ones are escalated to human approval (fail-safe).

Plugin de proveedor opcional para dsh-skill-pack-security: registra la edición skills/ (zh) o skills-en/ (en) del pack en ctx.skills. Incluye ambas ediciones integradas en pack/.

Aprobaciones de «Permitir para esta tarea» con alcance de turno: permite automáticamente las escaladas `danger-full-access` coincidentes solo para la tarea actual, y luego caducan.

Soporte de sandbox multiplataforma de Microsoft.

Analiza skills y configuraciones MCP en busca de inyección de prompts, homóglifos, Unicode oculto, comandos de shell peligrosos y fugas de credenciales.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

Transport-level authentication gate for the DeepSeek Harness Web GUI with server-side sessions, HttpOnly cookies, IP-based login throttling, and an scrypt password CLI.

Deterministic code security review: 40+ rules, secret entropy detection, staged-diff review, SARIF export, baseline acceptance and SBOM-lite dependency inventory.

Rules execution engine for dsh: parses AGENTS.md, hard-blocks rule-violating tool calls, text-based B/D rule auditing, /guard command, version-guard for versioned files, and free-zone support (engine skips free-zone sections).

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web panel, and allowlist.

Añade comprobaciones de políticas para operaciones peligrosas, redacción de salida y un flujo de trabajo de revisión de seguridad.

Modo de aprobación manual («Modo manual» / «Modo preguntar»).

Auditoría de solo lectura de la higiene de credenciales de la flota de agentes: permisos de archivos de credenciales, credenciales incrustadas en remotos de git (enmascaradas en la salida) y conteo de tokens de proveedor en texto plano; sin dependencias y determinista.

Higiene de texto como plugin de dsh: sanea texto no confiable, detecta caracteres invisibles, limpia el formato generado por LLM y escapa la inyección de fórmulas CSV.

Pre-install supply-chain poison scanner for DSH plugins: AST (JS-X-Ray) + deobfuscation + regex heuristics, exits non-zero on findings for CI gating.

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.

Live CVE/supply-chain audit for your workspace's own project dependencies (npm/pip/go), backed by OSV.dev, with a `cve_audit` tool plus optional automatic re-scan on lockfile changes.

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

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Blocks agents from reading or writing sensitive files (.env, credentials, key material), masks leaked secret-shaped values in tool results, keeps an audit journal, and exposes safe sg_* inspection tools that never print raw values.

Destructive-command interception gate for dsh: parses shell semantics, judges risk against 41 built-in rules, and holds irreversible rm -rf, git reset --hard, and git push --force style commands at a confirmation gate.