Skip to content

ai-safety 6

  • dsh-auto-review v0.12.16 Verified Web UI 234

    Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.

    dsh plugin add dsh-auto-review
  • dsh-approve-for-me v0.2.4 Verified Web UI 18

    Rule-gated automatic approval for DeepSeek Harness sandbox escalations with an optional LLM reviewer and native human fallback.

    dsh plugin add dsh-approve-for-me
  • dsh-guardian-approval v0.1.1 Verified Web UI 2

    Independent Codex Guardian-style approval reviewer for DSH.

    dsh plugin add dsh-guardian-approval
  • dsh-perm-gate v5.1.0 Verified Web UI 2

    DSH permission-gate for the DeepSeek Harness 0.1.5 line: a single self-sufficient, deterministic-first, fail-closed gate covering P0 hard-deny -> P1 session grant -> P2 static rule (allow/deny) chain -> P3 optional LLM semantic classifier -> P4 ask, with

    dsh plugin add dsh-perm-gate
  • dsh-jev-guardrails v0.1.1 Verified

    DeepSeek Harness plugin: Jev-backed guardrails for prompts, tool calls, tool results, and model responses.

    dsh plugin add @codebam/dsh-jev-guardrails
  • dsh-ccs-security v1.0.3 Verified

    Runtime security guard for DeepSeek Harness (DSH) β€” blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.

    dsh plugin add dsh-ccs-security