@jypjypjypjyp/dsh-guardrail
工具调用规范守卫:对 agent 工具调用参数做字符串匹配,命中危险行为拦截并注入原因(deny),或放行但注入警告(warn),附规则管理面板
209 results
工具调用规范守卫:对 agent 工具调用参数做字符串匹配,命中危险行为拦截并注入原因(deny),或放行但注入警告(warn),附规则管理面板
Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.
Eight DeepSeek Harness plugins: persona, language guard, vision fallback, python workdir guard, windows encoding guard, cross-agent memory, image generation, and skill shell injection.
dsh-docker — typed, guarded container control for DSH: structured docker/compose tools, project-aware targeting, an approval gate for destructive ops, service-health context, and a replayable status-table renderer
Remind and block stale tool work until todo_write is reconciled in DeepSeek Harness
Codex-style Git workbench for DSH: workspace-scoped changes, diff, stage, commit, guarded branch operations, graph history, fetch, fast-forward pull, and upstream push through official plugin APIs.
Installation safety gate & data-protection guard for DeepSeek Harness: 60 static signature rules (31 high/24 medium/5 low) scan plugin sources for malicious install scripts, credential theft, obfuscation, persistence and network callbacks before 'dsh plugin add', plus 12 destructive-command patterns and workspace-boundary checks against accidental deletion. | 安装安全闸门与数据保护闸:60 条静态签名规则(31 高危/24 中危/5 低危)扫描插件恶意行为、持久化与外传,12 种危险命令模式与边界检查拦截误删。
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
Budget-LLM pool router for DeepSeek Harness: usage ledger, health tracking, Thompson-sampling adaptive failover across free-tier models, quality tier ladder, executor pool, paid-guard, web panel + reroute badge. 穷鬼路由器。
Compatibility governance for DeepSeek Harness: upgrade pre-flight gate, storage-format fingerprinting, $DSH_HOME backup, session migration, per-profile lockfile with rollback, and a machine-readable plugin x DSH compatibility matrix + CI workflow.
DeepSeek Harness guardrail that limits how many files an AI coding agent can edit per turn
Mingleng mcpguard for DeepSeek Harness 鈥?the first security plugin for DSH. Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell and credential leaks.
Tavily search provider for DSH with full search-control mapping, credential-backed key UI, and guarded rc.6 compatibility patches.
Popper: a falsification-driven correction loop for agent sessions — claim commitment, gate falsification, and mutually exclusive hypothesis revision, with an append-only evidence ledger
Codex-inspired Guardian approval reviewer for DeepSeek Harness
Session-linked Git worktree task board and guarded delivery workflow for DeepSeek Harness
Post-compaction premise-drift guard plugin for DeepSeek Harness: after a compaction summary drops a critical literal anchor (path, value, error code) it injects a one-shot notice telling the model what it may have lost and how to recover it from the log
Stop runaway agent loops in DeepSeek Harness: denies repeated identical tool calls and enforces a per-agent call cap, outside the model where instructions cannot reach.
Codex-style Guardian reviews, audit, and manual override for DeepSeek Harness
Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
Triage port conflicts: reuse your own live server, switch ports for others, precisely kill zombies
The authority layer for agentic AI, as a DeepSeek Harness plugin. Governs every tool call against your business rules via the TapPass /v1/govern policy decision point.
Research-first assistant for DeepSeek Harness: gently nudge the agent to investigate docs / code / community before edits, detect blocked research, and record every hint in the session log.
DSH boot-guard: dual-mode — standalone CLI for pre-boot diagnosis, and DSH plugin for runtime health check dashboard.