dsh-auto-review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
33 results
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible, self-checksummed risk reports.
A read-only mirror for installed DeepSeek Harness plugins: capability inventory with evidence, cross-plugin conflicts, and a diff of what changed since the last scan
FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. v1.0.0 (PRODUCTION-READY, protocol frozen): 协议冻结(v1.x 向后兼容)+ v0.14.0 全部 7 项 P0+P1 + 5 项 audit 修复(4 bug + 1 性能)。测试基线 567 passed。Thin
DSH local security audit tool: read-only scans of config, credential metadata, plugin provenance, session structure and network exposure; redacted, reproducible, locatable risk reports
HTTPS + login gateway for the DeepSeek Harness web surface: securely access your DSH Web UI from another machine on your LAN, or from the internet via port forwarding. Fail-closed defaults (loopback-only listener, no accounts until configured); setup and security notes in the README.
【实验性】只读安全审计模式插件(自动只读、工具级白名单、强制交付选择)· EXPERIMENTAL plugin for the read-only security audit mode (auto read-only, tool allowlist gate, mandatory delivery choice);日常使用推荐 dsh-presets 仓库的原生纯预设版。
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.
Read-side SIEM forwarder for DeepSeek Harness: normalises session activity to OCSF and ships it
Disk-usage audit for DeepSeek Harness (dsh) data directories: total size, per-directory breakdown, largest files, and oversized-file warnings (session logs can hit hundreds of MB). Zero runtime dependencies, read-only. CLI + agent-callable disk_audit tool.
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
Database connector bundle for DeepSeek Harness (dsh): SQLite/PostgreSQL/MySQL connections, schema introspection, read-only safety, write approval gate, and a JSONL SQL audit trail.
Pre-install supply-chain provenance checks for DeepSeek Harness plugins: verify the tarball you're about to install matches the source you read, before any code runs. Never executes the audited package.
DSH agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
Better config hub for DeepSeek Harness: one page showing sandbox mode, default model, workspaces, settings namespaces and copy-ready composition templates.
Turn DeepSeek Harness sessions into redacted, README-ready animated demos — as a local CLI or DSH plugin.
DSH sandbox extension: protect declared workspace subpaths (e.g. .git) from writes, and optionally grant extra writable roots under workspace-write, enforced for sandboxed CLI commands and the write/edit tools. 为 DSH 沙箱增加工作区子路径只读保护, 并支持在 workspace-write 下声明额外可写根.
A DeepSeek Harness (dsh) security plugin: blocks agents from reading or writing sensitive files (.env, credentials, key material), masks leaked secret-shaped values in tool results, keeps an audit journal, and exposes safe inspection tools that never print raw values.
Pre-write reuse firewall for DeepSeek Harness: before the agent writes a new helper/service, surface the existing implementations that already cover that intent. Deterministic retrieval (no LLM) backed by the Auto_code_audit capability channel.
Enhanced DSH workspace directory picker: cross-drive/root browsing, breadcrumb jumps, and risk/permission visual indicators
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII redaction, and a local configuration security audit that emits redacted, reproducible risk reports.
Container-isolated backend for the DeepSeek Harness code-execution seam: Code Mode programs run in a fresh container with no network, a read-only rootfs, and kernel-enforced memory, CPU, and pid ceilings
Plan 模式心智映射:read-only 权限显示为 "Plan",审批策略 never(拒绝即最终,不准申请权限),文件只读 + 网络搜索可用。
DeepSeek Harness plugin: predict (pre-install) and detect (post-install) duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services to prevent Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".