Security & Permissions

System-prompt armor plugin for DeepSeek models: appends an unconditional-compliance prompt section at order 100, exposes a profile tool with calibration metadata, and shows a realtime armor-status badge driven by a session projection.

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Authorized-security DSH collection: nine work modes (redteam coordinator, pentest, code audit, binary analysis, attack-defense, AV evasion, incident response, cloud security, CTF solving) and fifteen runtime plugins, managed from a settings page with one-click deploy, install, update and uninstall.

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

Single-bundle reverse-engineering and pentest security plugin: first-turn tool narrowing, domain routing, and 33 tools covering APK, web, native binary, protocol, malware and LLM samples — with unpacking, license-bypass and anti-analysis case playbooks, an H-CoT evaluation engine (semantic routing, /hcot command), a web workbench with a ledger-driven tool shelf, an on-disk case workflow (auto-persisted evidence chain, E-numbered validated findings, post-compaction resume), GitHub-based external tool discovery, and 361 on-demand reference docs.

Prevents request context bloat in DeepSeek Harness: catalogs MCP tools and skills under ctx.capability, exposes them in exposed/progressive/blocked tiers, and invokes low-frequency ones on demand via meta_search/meta_invoke, with a visual settings tab.

Read-only security and compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and a local configuration audit with redacted, reproducible reports.

Risk-gated approval automation for DeepSeek Harness: flash pre-classifies whether a write/command is irreversible — safe operations are auto-approved, dangerous ones are escalated to human approval (fail-safe). File-diff review with one-click revert and session-scoped snapshots (v0.5.1: precise snapshots via tool-call parameter tracing, incl. human-approval cases).

Secure remote access for the DeepSeek Harness Web UI: a login gate, MFA/TOTP, signed session cookies, optional admin/user/guest roles, in-browser workspace selection, and allowlisted remote file previews.

Red-team engagement mode: send one target organization name and a planner session runs a five-role execution team (recon, asset triage, vulnerability discovery, exploitation, internal pivot) at up to three concurrent agents, preflight-checking skills and resources and asking once for any missing key or VPS first, guided by a built-in first-run onboarding skill; scoring follows the merged intrusion scoring rules (8 categories / 25 points) with server-side caps, highest-privilege-wins and per-service dedup, and self-registered accounts never score; findings land in a local SQLite fact base with discovery timestamps, shown in a persistent right-side console of 12 tabs (asset mapping with a discovery timeline, agent roster, session/tunnel state, five-stage attack chain, scoring targets, a report that spells out how each score was obtained — actions, exact commands, credential provenance, tunnel build commands — a category-organised POC/EXP knowledge base and a skill library with per-skill usability verdicts); ships 23 native skills, 53 redteam_* tools and one-command self-update.

Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.

DSH plugin: Claude-style Chinese risk control & conversation autonomy for DeepSeek Harness web

Commit-time audit harness for AI coding agents: 24 git-diff rules (secrets, out-of-scope edits, prompt injection), HMAC-signed audit trail, snapshot rollback, and an MCP server with 84 tools. Installable via dsh plugin add.

Replaces the dsh web startup to allow binding 0.0.0.0, gated by username/password login: signed session cookies, /api route protection, an auth tab in the settings panel, and a reset CLI that rotates the signing key to invalidate all sessions.

Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev as a System One decision layer for agent selection, supervision, corrections, and approvals.

DeepSeek Harness provider that runs the subprocess seam inside a remote Upstash Box

PTES-based penetration testing plugin with Root-Orchestrator architecture for DeepSeek Harness.

Session-aware sandbox escalation compatibility plugin for DeepSeek Harness/DSH第三方模型会话沙箱升级兼容插件

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.

Jev-powered decision layer plugin for DeepSeek Harness