Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk tool calls at runtime, audits output secret patterns, and writes HMAC-chained local audit logs.

by of1102

Volcengine Ark web-search provider plugin for DeepSeek Harness

by zhengqiuyang

Compaction integrity for DeepSeek Harness — constraints from the compacted range are verified against the summary; what the agent was told to remember and silently forgot is reported loudly

by AntaresCorn

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

by TARS-snail

Approval guard for DeepSeek Harness: write/edit/editor/bash calls touching sensitive paths (.env, .git, SSH keys, .pem) become an approval ask.

Semantic risk grading and progressive authorization: classifies tool calls into safe/risky/redline, asks before irreversible actions, auto-allows only approved-and-succeeded signatures.

Blocks API keys pasted into the composer or written by tools, logs leak events, and scans the workspace for exposed secrets.

Global prompt-injection / context-virus defense for DeepSeek Harness: scans tool arguments, tool results, pre-model messages and the outbound stream; quarantine/block/monitor modes, canary trap, and a

by liyang52520

Password gate for the DeepSeek Harness Web GUI: first-run setup, brute-force lockout, audit log, and a management page inside Harness settings.

by zhengqiuyang

System-prompt surface drift gate for DeepSeek Harness — every section any plugin contributes to the assembled prompt is hashed and baselined; a silent rewrite of what the model is told fails loud

by lifecoder1988

Project secret management for the DeepSeek Harness: monorepo .env discovery, comment-preserving edits, and a DSH_ENV_FILES pointer your shell commands can source

by HandsYe

DeepSeek Harness bundle for MotoMoto's OpenAI-compatible endpoint: pi-ai provider route + Settings status card

Device-pairing gateway for DeepSeek Harness: by default it listens on 127.0.0.1:3443 over plain HTTP and reverse-proxies the local dsh at http://127.0.0.1:3080, so a loopback-only install works withou

by dongsheng123132

Offline content-addressed proof that temporary DSH policy waivers stayed within approved bounds

by Elaina-real

Tiered auto-review for DeepSeek Harness (DSH): static-rule safety net + LLM reviewer + human fallback. Auto-approve safe actions, auto-deny irreversible ones, ask a human for the rest. PURE VIBE CODING - not audited, use at your own risk.

by aa2246740

Fail-closed Creator Mode+ bridge for DeepSeek Harness, supervised externally by DSHX.

by uckkk

Hiking Safety

by xuxucodepractice-code

A deterministic pre-write claim guard for supported DeepSeek Harness file tools.

by dingchenhui0618-arch

Adversary review gate for DeepSeek Harness: an independent small model reviews destructive tool calls before they run, and reports every verdict. · DSH Adversary Review Gate: destructive tool calls are reviewed by an independent small model before execution.

by shuxue6662-a11y

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 cle

by blairlaird

Durable agent-to-agent mailbox for DeepSeek Harness: any MCP client or DSH session can address any other. Threads, receipts, search, broadcast, edit/withdraw, reactions. Local-only, zero dependencies, secrets redacted on ingest.

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log

by XiaoSong1223

Deterministic release-risk checks and quality gates for DeepSeek Harness

by shaneconner

Sign in to DeepSeek Harness model providers with a Claude Pro/Max or ChatGPT Plus/Pro subscription.