by julescules

Windows agent safety for DeepSeek Harness: preview risky calls, protect workspace boundaries, and explain audit decisions.

by 7starsseeker

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the

Reviews destructive shell commands with a model before they run, asks you to confirm or blocks them, and aborts a running command once it has deleted too many files.

by JohnXu22786

dsh plugin: desktop control - screen capture, pointer/keyboard injection, accessibility-tree semantic actions, with emergency stop, allow/deny rules, confirmation flow and idle standby

by ZhijiangTang

DSH plugin: block dangerous shell commands and secret leakage before execution (tools/pre-execute veto)

by ZSeven-W

DeepSeek Harness plugin for macOS desktop automation. Observes the accessibility tree, gates risky actions behind one-time approval, permanently refuses secure fields, and returns bounded visual evidence — through a native helper you build and grant locally.

by ethanrise

DeepSeek Harness Local Privacy Gateway: desensitizes sensitive fields in CSV/XLSX files before the data is sent to AI.

Hands secrets and PII to the agent without them entering its context, with checksum-validated extraction and masked content classification.

by zzzmmmnn

Remote-only OpenKapsel workspace bridge for the DeepSeek Harness: replaces host filesystem and shell tools with a fail-closed remote tool set. Self-hosted alternative to cloud agent sandboxes.

by Ukashi0

Local-first memory governance for DeepSeek Harness: scoped recall, provenance, conflict review, and a Web dashboard.

Text hygiene as a dsh plugin: sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.

by edynasty

DSH OpenCode Go provider plugin

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and st

Arms an explicit per-session scope contract from a `$stop-that-shit` directive and audits every tool call against it; unarmed it is inert. A DSH bundle wrapping lennney/stop-that-shit (MIT). Do not in

by 863683348

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 und

by fengbai2233

DSH plugin: two tools, pwsh_script and run_argv, structurally eliminate Windows PowerShell's command-string quoting escaping errors. · Two DSH tools that remove the PowerShell command-string quoting layer: a multi-line body passed as one argv element with structured $DSH_ARGS data, plus a shell-free argv runner.

by guhanfei-ai

Human intent verification and cryptographic action authorization for AI agents. AI can propose an action. Only a human can authorize it.

by JWE24-code

Deterministic, one-way PII anonymizer at the start of the DeepSeek Harness agent loop

by wentao75

DSH remote-access authorization page that shows the current process browser-session URL as a clickable link or QR code, behind an optional authority/subnet allow-list and PIN.

by raomaiping-hash

Remote access login gate for DeepSeek Harness Web: password wall, /api gating, session cookies, Remote Access settings.

Plain-language trust dashboard for the dsh trust family: aggregates the nine channels (injection interception, write denials, egress blocks, custody-chain verification, tool-surface and prompt drift,

When using a reverse proxy, allow the first access without a token

by ChaoJie0

Zero-intervention permission gate for DSH agents on macOS: auto-allows local writes made reversible by git or Time Machine, blocks network, package installs, process control and sensitive-path reads,

by Wisdoverse

GitHub and GitLab CLI authentication through DSH credentials or environment tokens, with workspace-local SSH deploy keys and plugin settings.