catalog / security
Security & Auth
Every Security & Auth plugin in our curated awesome list, synced from GitHub.
Plugins that extend the harness's safety seams: authentication and OAuth providers, permission policies, audit trails and guard extensions. They hook the interception points around tool execution and model requests, complementing the built-in sandbox tiers and approval system.
Synced from our GitHub list · Catalog updated 2026-09-30
264 plugins
tencentmeeting-cli
by tencentcloud
Tencent Meeting command-line tool with OAuth2 authorization for meeting, recording and attendance-report management.
dsh-auto-review
by perrylink
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
dsh-permission-rules
by perrylink
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
dsh-remote
by scspotato
Native Android client to remotely control DeepSeek Harness (DSH) from your phone
dsh-secure-audit
by pensivefei
Read-only security & compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and local configuration audit with redacted, reproducible reports.
jevcore
by perrylink
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
dsh-remote
by mrrisega
通过手机浏览器和中继/自建服务远程访问并操作本机 dsh web。
dsh-sandbox-escalation-fix
by hakureimonika
Project per-session sandbox escalation schemas and suppress redundant escalation retries in DSH.
sofagent
by kongfangxun
sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 25 codified audit rules, tamper-evident chain, snapshots, and an MCP toolset (104 tools, 11 plugins). Everything can be FDEing.
dsh-agy
by chaos-03x
Google Antigravity (agy) OAuth auth + model access plugin for DeepSeek Harness: multi-account pool, 429 rotation, device fingerprinting, CLI and web login.
dsh-pentester
by fb0sh
Orchestrates authorized reconnaissance, analysis, validation, reporting, and isolated Docker-based security tooling.
deepseek-harness-auth
by taichuy
Out-of-tree authenticated web proxy bundle for DSH web profile.
dsh-jev
by buberlo
Jev-powered decision layer for DeepSeek Harness
dsh-coding-subscription-oauth
by lninghaha
DeepSeek Harness coding-subscription OAuth: SuperGrok / Grok Build, ChatGPT Plus Codex, Kimi Code, Claude Code. No API-key pasting.
dsh-jev-interceptor
by asktheway
Classifies tool-call risk and session-reference value, gating approvals and retaining higher-value context with fail-closed fallback.
dsh-clawrouter
by blockrunai
A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.
dsh-remote-mobile
by iceapriler
Adds authenticated LAN and Tailscale access to the DSH web console with QR pairing, persistent device sessions, and mobile UI adaptations.
dsh-defend
by perrylink
Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events
dsh-group-photo
by senmuuuuw
Polaroid-style group photo wall for the DSH beta community — GitHub OAuth sign-in and whitelist validation, wrapped as a DeepSeek Harness skill.
dsh-sandbox-escalation-fix
by inmny
Prevent repeated same-or-lower sandbox requests from failing while preserving genuine escalation approval checks.
dsh-auth-gate
by tecfancy
Protects DSH Web HTTP and WebSocket surfaces with login sessions and provides CLI tools for users, TOTP, skills, and an optional local proxy.
dsh-jailbreak-mode
by bainianling
A standalone jailbreak-mode plugin for DeepSeek Harness, intended for authorized security research and educational testing.
agent-guard
by mokuyoaxis
Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliability infrastructure, not a sandbox.
dsh-security-audit
by omdsh-dev
Local security audit for DeepSeek Harness — scans config, plugin sources, sessions and network exposure into a read-only risk report.
dsh-codex-oauth
by wnjxyk
Use your OpenAI subscription with DeepSeek Harness to access GPT models, image generation, and web search.
weiwen-law-dsh
by shaky77
Adds pre-execution, pre-step, and post-execution gates plus read-only audit tools for causal risk, boundaries, and bug-stop decisions.
dsh-auth-gateway
by xbzbing
Places password and optional TOTP authentication in front of the DSH Web HTTP and WebSocket surface.
dsh-one-gateway
by tiantianflow
Private DSH One Gateway — loopback, identity-first ingress for DeepSeek Harness
dsh-remote
by hyna-hla
Pair a mobile client with DSH for remote sessions, approvals, MCP/file browsing, and token-gated host access.
dsh-mask
by perrylink
PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled storage domain, never log plaintext, and expose /mask and the mask_test tool