dsh-policy-drift-proof
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
177 results
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
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
DeepSeek Companion Enterprise — DeepSeek Harness 企业级伴侣插件:安全审计与 DLP、团队协作与知识管理、任务编排、多模型竞技场、执行轨迹分析、Prompt 工程工作台、API 成本治理。
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.
Cybersecurity and reverse-engineering skill router for coding agents (pi / DSH / Codex CLI / Claude Code). Explicitly invoke when reverse-engineering, security analysis, CTF, or pentesting workflow is required.
Security for DeepSeek Harness in two layers: source-backed pre-install vetting plus fail-closed runtime guardrails and HMAC-chained audit logs. Zero runtime dependencies.
Decision-driven AI company orchestration with HR governance, monetary budgets, model discovery, and deterministic audit for DeepSeek Harness
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
Content-addressed audit indexes across independent DeepSeek Harness evidence producers
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
KISS's Law (Weiwen's Law) universal causal engine (white-box presentation). DeepSeek Harness (Cordis) plugin implementation.
Scan agent skill packages for static security risks. Use for skill audit, security check, prompt-injection review, suspicious scripts, unsafe dependencies, zip package review, and pre-install skill review. Not for runtime monitoring.
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
DeepSeek Harness 工作区管理工具集:查看、创建注册、重命名、删除工作区记录(纯注册,不触碰磁盘目录);破坏性操作(删除注册、改注册路径)走用户审批 fail-closed。
NeevSandbox execution providers for DeepSeek Harness
dsh plugins ported from eco-agent: permission gate, audit chain, memory tree
Independent Codex Guardian-style approval reviewer for DSH.
Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏:拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。
DSH microsandbox bundle: Linux microVM shell executor and ctx.sandbox provider (msb run) with workdir/env preservation, fail-closed probing, and shell-free argv construction
BugTraceAI penetration-testing mode for deepseek-harness (dsh): pentester persona, bundled runbook skill, and the BugTraceAI MCP bridge in one installable profile bundle.
Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
One-click control that closes a session's persistent bash terminal (dual-face: /exit-bash command + session-header button) so the sandbox mode can be switched