SEMANTIC DIRECTORY · plugin-directory-semantic-v3-19
Tool-Execution Policy Enforcement
在工具执行管线中以持久化规则强制执行 allow、deny、ask、出站白名单、写Permissions范围、文件修改额度、信息流/污点控制和环路熔断等策略。排除人工审批交互、危险命令专用拦截和企业策略配置治理。
Leaf membership
55 plugins
@agenticcontrolplane/dsh@agenticcontrolplane/dshCatalog AnalyzedAgentic Control Plane for DeepSeek Harness — check every tool call against your policies before it runs, and keep a durable record of what was allowed and why.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.4Evidence updated2026-09-26Public signals45 downloads@jiesou/dsh-stream-rules@jiesou/dsh-stream-rulesCatalog AnalyzedInject rules when needed, without wasting context. DSH port of opencode-stream-rules.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.7Evidence updated2026-09-25Public signals311 downloads@ramen-ai/dsh-ramen-guard@ramen-ai/dsh-ramen-guardCatalog AnalyzedFail-closed semantic policy guard for secure DeepSeek Harness tool execution.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-26Public signals96 downloads@tappass/dsh-governance@tappass/dsh-governanceCatalog AnalyzedThe 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.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.1Evidence updated2026-09-25Public signals793 downloads@yadsh/dsh-session-scope@yadsh/dsh-session-scopeCatalog AnalyzedPer-session workspace visibility scopes for DeepSeek Harness.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.7.5Evidence updated2026-09-25Public signalsNo public usage signalscorrectovercorrectoverCatalog AnalyzedAI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact2.4.17Evidence updated2026-09-26Public signals2928 downloadscue-skills#cue-omni-reader-guardsensedeal/cue-skillsCatalog AnalyzedHardening guard for mcp__omni__parse in DeepSeek Harness: a tools/pre-execute listener that denies private/reserved host URLs (SSRF), enforces an allow-list or ask (consent), and is fail-closed when allowedRoots is empty.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals7 starsdsh-agentfuse-pluginMkaliezZ/dsh-agentfuse-pluginCatalog AnalyzedDeterministic fail-closed tool-call authorization for DSH with evidence: allow/block/ask policy gate plus approval-chain deferral.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals3 starsdsh-approval-firstjoao-paulo-santos/dsh-approval-firstCatalog AnalyzedApproval-first edit/write for DeepSeek Harness: shadow tools ask the user BEFORE a mutation the standing sandbox policy would deny, so the model never has to repeat a tool call with sandbox_permissions. In-policy writes stay silent, out-of-policy targets get an approval card on the first call.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-approval-guardiankaruboniru/dsh-approval-guardianCatalog Analyzed模仿codex auto-review 的自动审批机制CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals2 starsdsh-approval-llmdsh-approval-llmCatalog AnalyzedModel-based permission approval: an approval-request answerer backed by a separate reviewer model.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.1.6Evidence updated2026-09-20Public signals7 stars · 806 downloadsdsh-approve-for-mewcwplaygitbub/dsh-approve-for-meCatalog Analyzeddsh增加类似替我审批的能力CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-auto-modea1140314368/dsh-auto-modeCatalog AnalyzedDSH auto-mode: LLM-based safety interceptor (allow/deny/ask) for dangerous tool calls, as a selectable permission presetCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-auto-mode@nanmicoder/dsh-auto-modeCatalog AnalyzedAdds an Auto permission preset between Workspace Write and Full access: routine work stays in the official workspace-write sandbox while the current session model reviews escalation and destructive calls, granting one exact wider access once, asking when the intent is ambiguous, and denying critical paths.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.9Evidence updated2026-09-19Public signals161 stars · 3409 downloadsdsh-auto-reviewAtropinolTT/dsh-auto-reviewCatalog AnalyzedDSH Auto Mode — native security review plugin for DeepSeek Harness: pre-execution rule interception + delivery-time independent subagent review. Built for long-running agents.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals2 starsdsh-auto-reviewXinlong-Wu/dsh-auto-reviewCatalog Analyzedadds an auto-review permission preset to DeepSeek Harness. Same Codex auto reviewCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals1 starsdsh-auto-reviewaccpowered/dsh-auto-reviewCatalog AnalyzedLLM 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.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signalsNo public usage signalsdsh-autogatewangxing-git/dsh-autogateCatalog AnalyzedDeepSeek Harness 自动审批Plugin：在 workspace-write 沙箱之上叠加确定性规则 + LLM Security审批，自动模式不放宽沙箱、fail-closed。 Safe auto-approval for DeepSeek Harness — deterministic rules + LLM review on top of the workspace-write sandbox. Auto mode without ever granting full-access.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals3 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.