@suagr_xl/dsh-safety
A safety harness plugin for DeepSeek Harness (DSH): protected-path enforcement, trash-based safe_delete with undo, last-known-good composition snapshots, pre-restart composition checks, and an audit journal.
344 results
A safety harness plugin for DeepSeek Harness (DSH): protected-path enforcement, trash-based safe_delete with undo, last-known-good composition snapshots, pre-restart composition checks, and an audit journal.
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.
Real-time attention alerts for DeepSeek Harness: a global banner plus flashing workspace entries when the agent is blocked (approval request / sandbox denial), with an audible chime and OS-level notifications for new blockers.
DeepSeek Harness bundle that routes real sandbox escalation prompts through a dedicated approval reviewer
DSH 规则执行引擎 v3:容器解析 AGENTS.md + 理解器 + 匹配机 + 执行框架
DSH AI 代码安全审查插件:secure_scan/secure_diff/secure_fix_verify/secure_report/secure_export/secure_baseline/secure_deps/secure_policy_show/secure_policy_set 九工具,40+ 确定性规则、密钥熵检测、git diff/staged 审查、SARIF 导出、基线接受与 SBOM-lite,零运行时依赖。
Pre-install supply-chain poison scanner for DeepSeek Harness plugins: AST analysis (NodeSecure JS-X-Ray) + deobfuscation decoder + regex heuristics to catch credential exfiltration, dynamic code execution, obfuscated imports, and install-time scripts.
Plugin insight center — one answer to '哪些值得装': requirement matching (plugin_guide), environment recipes (recipe), health scoring (plugin_rank), static security scanning (plugin_audit), and a single install verdict (plugin_verdict)
DeepSeek Harness plugin (temporary, pre-upstream-fix): automatically injects a CPython tempfile shim (PYTHONPATH -> sitecustomize) into every confined shell command on the Windows sandbox, so python/pytest tempfile use works with zero extra tools, zero model-context overhead, and zero escalation.
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.
X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.
Let a local DeepSeek Harness Agent use BailingHub to query data, update records, and run permitted actions in your online store, SaaS, or other admin system.
Structured, machine-readable CI output for DeepSeek Harness (dsh): session event capture with JSON/NDJSON reports, JUnit XML, semantic exit codes, artifact collection and privacy redaction. Ships as a dsh profile bundle and a standalone CLI.
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
Fifth DeepSeek Harness mode with configurable Codex, Claude Code, or DSH audits, user-approved remediation turns, progressive Cordis/skill elevation, safety pauses, and Web/TUI review controls.
Hawkeye Scan Workbench - AI-driven source-code security scanning for DeepSeek Harness (DSH): 5 model tools + /hawkeye web UI + JSON/Markdown/HTML vuln reports. Zero-dependency Cordis plugin.
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.
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。
Seatbelt (libsandbox) sandbox provider for the DeepSeek Harness sandbox seam on macOS: a cordis plugin that replaces @deepseek-ai/dsh-sandbox-local's seatbelt rung via a prebuilt seatbelt-run launcher — no dsh source changes, no PR required
Portable DSH WebUI skill security inspection with local rules and optional model review
Workspace Only switch for DeepSeek Harness: confine file access of every sandbox mode to the session workspace
Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.
NeevSandbox execution providers for DeepSeek Harness
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.