Security & Permissions

Read-only DSH plugin auditor with static scanning, current-session model review, and confirmation gates.

One-time Full access switch for DeepSeek Harness: new sessions (workspaces and conversations) start with danger-full-access and skip the per-session Full access confirmation; installable as a dsh bundle or via patch scripts.

Security-focused Feishu (Lark) channel for DeepSeek Harness: allowlisted remote-agent access with workspace-scoped paths, symlink checks, risk-based approvals, session isolation, redacted logs, and bounded message queues.

AI-driven source-code security scanning workbench: 5 model tools (start/finding/status/report/list) plus a /hawkeye web UI and JSON/Markdown/HTML vulnerability reports; zero-dependency Cordis plugin, installable as agent preset or npm package.

Uses an isolated LLM review to approve or reject DSH sandbox permission requests.

Static-only plugin gate and clinic for DSH: audit before install, hash-and-capability lock after install, local fingerprint peer search over GitHub topic:dsh-plugin, and mechanical detox. Never executes the target plugin.

LLM approval answerer for sandbox escalations beyond workspace-write: a deterministic regex filter first, then a clean-context reviewer model; humans are asked only when it is unsure. Requires the bundled core patches.

Named user credentials the model uses by reference: values are entered on a Settings → Credentials page and injected into each shell execution as DSH_CM_* variables instead of being printed into the transcript, with credential_read as the documented last resort.

Compaction quality / hallucination detector: when a conversation span is compacted, check on two axes that key information survived 鈥?FIDELITY (assertions in the summary must be found verbatim in the original leaf events, else flagged as fabricated) and C

Step-0 observation probe for dsh-compaction-audit: logs every compaction/* session event and probes whether shadowedSeqs still resolve to readable events in session.events. Observe-only; never injects, never blocks.

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

Reliable todo panel that survives restarts (official panel only re-renders on write — fixed via projection pre-warm) with three-state completion verification: evidence exists → verified, fake evidence → blocked, no evidence → unverified badge; settings toggle to fall back to official behavior.

一个可直接链接到 DeepSeek Harness（DSH）Web profile 的独立安全检查插件。在安装或使用不受信任的 Skill 前，先执行浏览器本地粗检，再由用户决定是否调用 DSH 已配置的大模型进行结构化复核。

Forge quality gates for DeepSeek Harness (dsh): task gates, read-before-edit, bash hazard interception and quality scoring, driven by the forge CLI through DSH's typed interception points.

Independent Codex Guardian-style approval reviewer for DSH.

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

Pre-install supply-chain checks for DeepSeek Harness plugins: verify the tarball you are about to install matches the source you read, before any code runs.

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.

Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 per-category switches and an audit trail.

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.

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

DSH plugin: password gate for remote (non-loopback) /api access (passwordless by default), unblock the loopback-pinned privileged endpoints, restore everything on uninstall, and give the local 127.0.0.1 user the native OS folder picker for workspace selec

Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting

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