by Duoasa

A public agent skill for faithful integration of canvas, WebGL, shader, scroll-driven, pointer-reactive, and third-party animated components.

by feely0208

Least privilege check: container running as root/privileged, IAM wildcard permissions, fully open CORS, token requesting admin access.

by Asuna486-desuwa

Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting

DaMeng DM8 Database Read-Only Security Assessment Plugin: 13 domains, 60 checks (53 in-database + 7 host-side OS/SSH), six-state conclusions without scoring, MLPS 2.0 (GB/T 22239-2019) control point mapping (Levels 2/3/4 selectable), outputs single-file HTML report.

by feely0208

Minor Protection: Check whether personal information of individuals under 14 years old has guardian consent, dedicated rules, and age thresholds.

by JohnXu22786

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 sg_* inspection too

by chunfenxiazhi-collab

Stability audit for installed dsh plugins: static risk grading (hook surface, startup work, inject, entry, dep ranges) plus optional isolated install verification.

by feely0208

External content trust boundary: Check whether the agent treats content from web pages, files, or emails as trusted instructions.

by W-SING-HUNG

Job Resume Studio: Paste the JD, and AI rewrites your resume to match the position — based only on real content, no fabrication — DeepSeek Harness Plugin

by vitas

Cut LLM costs: a Jev (System One) classifier vets each turn against a declarative policy and recommends the subagent model route, so routine work runs at flash rates while the main model keeps the har

by BaqiF2

No project description is available for this repository yet.

by yiyunet

A learning plugin that runs in the DeepSeek Harness input area: turning "collect → distill → associate → upgrade → precipitate → reuse" into runtime capabilities featuring interactive guidance, preset management, review-and-ingest, and system health checks. DeepSeek Harness plugin: a four-entry learning workspace.

by 173787247

Hard-stops further tool calls after a configurable per-session budget is reached.

by meliwanx

Secure DeepSeek Harness plugin for official WeCom, DingTalk, and Feishu/Lark CLIs

by cainiao1992

CodeBuddy (Tencent IOA) as a native DeepSeek Harness llm provider: browser OAuth login, token auto-renewal, credential storage, and /v3/config model sync.

by chupeter854-lang

Automatically moves focus into the card when the approval card appears; press Enter to approve or Esc to reject (DSH Web / Desktop client plugin).

by zz12hui

DSH Tool Plugin: Copywriting De-AI-Fication Audit (Six-Dimension Scoring + Per-Sentence Tagging + Revision Techniques), directly invoke deai_audit / deai_audit_config within conversations.

by dshplugin-me

Find DSH plugins and security-scan them before install

by wood007924

Press Enter to approve a pending permission request in DeepSeek Harness (dsh) - no mouse.

by ZeroClave

Privacy firewall for DeepSeek Harness: detect and redact sensitive text before sending.

by samirliu

Deterministic goal-completion gate for DSH: contract-first AC grammar, re-runs every verify command itself (zero model trust), binds verdicts to a tree digest, denies false completion on update_goal/u

by feely0208

Check the dependency tree for poisoning and risk surface: install-time execution scripts, overly broad version ranges, non-registry sources

by ChenLaoshiYF

Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, and credential leaks.

by chenjie1129

Evidence-gated completion and trusted code verification for DeepSeek Harness agents