Plugins

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Vollständiges Reverse-Skill-Paket (85 SKILL.md) als DeepSeek-Harness-Cordis-Plugin: Skill-Router für Reverse Engineering, autorisiertes Pentesting und Security-Forschung.

Auto-Modus für DeepSeek Harness (dsh): ein Auto-Eintrag im Berechtigungs-Selektor, dessen Freigabe-Prompts von der OpenGuardrails-Policy statt von einem Menschen beantwortet werden — inklusive der vollständigen OGR-Guard-Engine darunter. Keine Kernänderungen.

Remote DeepSeek Harness with full server-side API access (`settings.*` / `credentials.*` / `host.listDirectory`). Token-gated reverse proxy, per-device sessions, phone invite QR, fence self-check, optional approval / CIDR / idle timeout / local TLS, WebSocket/SSE.

Lokales Sicherheits-Audit: Konfiguration, Plugin-Herkunft, Sitzungen, Netzwerk-Exposition — rein lesender, geschwärzter Risikobericht.

Login-Gateway für die DSH Web UI: Passwortschutz mit Ersteinrichtung, bcrypt plus Verschlüsselung im Ruhezustand (AES-256-GCM/HMAC), Brute-Force-Sperre, Audit-Log, TLS 1.2+ mit 80→443-Weiterleitung, CSRF-Schutz und Anti-Framing.

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

Always-on dependency security for DSH plugins: tracks exact installed paths, OSV vulnerabilities, npm releases, and breaking-change signals, then routes project evidence to a DSH Agent.

Alternative plugin market for DSH: curated catalog plus live GitHub browsing, zh/en cross-language search, a fail-closed pre-install static security audit with an install-hook block, and per-plugin README viewing with garbled-encoding repair.

Remote access & authentication for DeepSeek Harness web UI: account/password login gate, MFA (TOTP), signed session cookies, role-based access, in-browser directory picker, account management settings, fully localized in English and Chinese.

Password + TOTP two-factor authentication gateway for the dsh web UI: every HTTP request and WebSocket upgrade is refused until login, with per-source lockout, global rate limits and one-time backup codes.

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

Plugin-Store im Stil des Steam Workshop für die DSH Web UI: Community-Plugins durchsuchen, suchen und mit einem Klick installieren, mit Mirror-Beschleunigung, Fortschrittsanzeige, Sicherheitsprüfungen und chinesischen Beschreibungen.

Template-driven code review skill: five-step review flow, critical/medium/minor severity grading, four-dimension scoring (quality, security, performance, maintainability), dual text and HTML report output, and an on-demand reference knowledge base.

Schwärzt unterstützte Geheimnis-Muster in der Exportkopie von `session-telemetry/record`, bevor konfigurierte Telemetrie-Backends sie erhalten.

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).

Tested-curation lab for DSH plugins: every entry passes real install/static-scan gates in an isolated environment, with full logs and reproduction commands (Chinese-first).

Agentic Control Plane für DeepSeek Harness — prüft jeden Tool-Aufruf vor der Ausführung gegen Ihre Richtlinien und führt einen dauerhaften Nachweis darüber, was warum erlaubt wurde.

Optionales Provider-Plugin für dsh-skill-pack-security: registriert die skills/-(zh-)oder skills-en/-(en-)Edition des Pakets in ctx.skills. Liefert beide Editionen eingebettet in pack/.

Durchsucht Skills und MCP-Konfigurationen nach Prompt-Injection, Homoglyphen, verstecktem Unicode, gefährlichen Shell-Befehlen und Zugangsdaten-Lecks.

DeepSeek Harness community Bundle for the skill-security-guard static scanner

Provenance-aware execution security for DeepSeek Harness. Track sensitive data across tool calls and stop risky side effects before execution.

Ecosystem-wide plugin health audit: syncs the dsh-plugin topic into a local scored catalog (maintenance / docs / npm + weekly downloads / ecosystem, 0-100, A-D), static security scan with high-finding grade veto, star history snapshots, web leaderboard and agent tools.

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.