dsh-prompt-shield
A runtime prompt-injection shield for DeepSeek Harness tool results.
267 results
A runtime prompt-injection shield for DeepSeek Harness tool results.
DSH 插件安检机 — install-time static security auditor for DeepSeek Harness plugin bundles. Zero dependencies, zero install scripts, zero build step.
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.
Independent Codex Guardian-style approval reviewer for DSH.
PRO-LONG-style programmatic memory for DeepSeek Harness: appends every session event to a per-workspace log.txt that the agent retrieves with grep/python. Built-in write probe, /prolong status command and permission-deny counter.
Static DSH plugin compatibility audit before installation, plus bounded Loader lifecycle observation
Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏:拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。
DSH microsandbox bundle: Linux microVM shell executor and ctx.sandbox provider (msb run) with workdir/env preservation, fail-closed probing, and shell-free argv construction
Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance, and a web control page in Settings → Plugins.
One-click control that closes a session's persistent bash terminal (dual-face: /exit-bash command + session-header button) so the sandbox mode can be switched
Fail-closed DSH compatibility guard for redundant GPT/Codex sandbox escalation arguments
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
DSH profile plugin: unconfined (GPU-capable) session sandbox plus per-operation user approval for writes outside the workspace or to protected files.
Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).
A security-conscious registry and installer for external CLI tools exposed through DeepSeek Harness.
Disk-usage audit for DeepSeek Harness (dsh) data directories: total size, per-directory breakdown, largest files, and oversized-file warnings (session logs can hit hundreds of MB). Zero runtime dependencies, read-only. CLI + agent-callable disk_audit tool.
DSH Web GUI plugin: session-scoped "Allow for this session" option in the approval dialog (per-mode standing grants, localStorage)
Dependency-installation guard for DeepSeek Harness: classifies package-manager commands as ALLOW, ASK, or BLOCK before execution.
Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting
Model-visible redaction plugin for DeepSeek Harness: redacts secrets from model input and output streams
DSH web plugin: play a notification chime when the agent asks the user a question (ask_user_question / plan review) or requests approval (sandbox escalation, tool approval).
Native Auto Review for DeepSeek Harness with automatic host compatibility selection