# PerryLink

> Open-source publisher. Listings imported from github.com/PerryLink — credited to the original author with their license.

- **Listings:** 10
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/perrylink
- **Website:** https://github.com/PerryLink

## Published listings

- [Threat Model](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-threat-model) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-skill-pack-security-threat-model`
  新功能/新系统的轻量威胁建模：固定对象→划定范围与信任边界→资产清单→STRIDE 逐资产威胁表→攻击树（可选）→缓解与优先级，产出可进设计评审的威胁模型文档。为新功能/新改动做设计阶段安全评审、梳理信任边界或画攻击树时用；与安全边界无关的纯 bug 修复、已有成熟建模流程的团队不展开本流程。
- [Vuln Intel](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-vuln-intel) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-skill-pack-security-vuln-intel`
  漏洞情报检索与判定：NVD/CISA-KEV/GHSA/OSV 四处权威源的查询命令、响应解读与误判判据，把 CVE/GHSA 编号变成"是否在野利用 × 是否影响本项目"的带证据结论。给定 CVE/GHSA 编号查详情与影响、判断在野利用状态或写漏洞简报时用；无编号的泛漏洞科普不展开。
- [Dsh Plugin Guide](https://agentstack.voostack.com/l/skill-perrylink-dsh-plugin-guide-dsh-plugin-guide) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-plugin-guide-dsh-plugin-guide`
  Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by the dsh-plugin-guide knowledge base.
- [Dsh Mcp Panel](https://agentstack.voostack.com/l/mcp-perrylink-dsh-mcp-panel) — MCP server · Free · security-reviewed — `agentstack add mcp-perrylink-dsh-mcp-panel`
  Read-only runtime management panel for the official DeepSeek Harness MCP client: /mcp command + Settings MCP tab with status, tools, errors, reconnect counts, sanitized display and controlled patch suggestions (Apache-2.0, dsh-plugin).
- [Incident Response](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-incident-response) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-skill-pack-security-incident-response`
  agent 环境安全事件响应：分类→控制蔓延→取证留痕→恢复→复盘的分步处置流程，覆盖密钥泄露、提示注入触发、依赖投毒、未授权操作四类事件，每条处置附命令证据。DSH/agent 环境出现疑似安全事件需要按流程处置与复盘时用；日常开发与例行维护不用。
- [Supply Chain Review](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-supply-chain-review) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-skill-pack-security-supply-chain-review`
  PR/新依赖快速供应链评审：危险 install/postinstall 脚本检查、typosquat 相似名判断、可复现构建验证，每项附误报判据与通过/要求修改/阻断三档决策阈值。评审引入新依赖的 PR 或需快速给出新增依赖风险结论时用；与新增依赖无关的普通代码评审不用。
- [Prompt Injection Review](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-prompt-injection-review) — Skill · Free — `agentstack add skill-perrylink-dsh-skill-pack-security-prompt-injection-review`
  面向 agent 项目的提示注入面审查：AGENTS.md、技能目录、工具描述、MCP 来源与网页抓取内容的注入面检查清单，含数据与指令的区分判据和缓解项。审查对象是会被注入模型上下文的内容且需评估注入风险时用；与模型上下文无关的代码或配置评审不用。
- [Secret Scan](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-secret-scan) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-skill-pack-security-secret-scan`
  凭据/密钥暴露审计：gitleaks、trivy 全历史扫描命令与参数、告警误报分级判据、脱敏报告规范、按轮换→撤销→清除历史→CI 门禁排序的修复流程。任务涉及仓库内密钥/token/密码/私钥的检测、历史提交泄露排查、扫描告警真伪判定或泄露报告撰写时用；与凭据无关的常规代码审查不用。
- [Dependency Audit](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-dependency-audit) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-skill-pack-security-dependency-audit`
  依赖供应链审计：pnpm/npm audit 输出与退出码解读、license 与投毒风险检查清单、锁文件漂移检测命令。任务要求审计项目依赖的已知漏洞、许可证风险、可疑包或 lockfile 一致性并出结论时用；单独安装/升级某个依赖或纯功能开发不展开本流程。
- [Security Audit](https://agentstack.voostack.com/l/skill-perrylink-dsh-skill-pack-security-security-audit) — Skill · Free · security-reviewed — `agentstack add skill-perrylink-dsh-skill-pack-security-security-audit`
  仓库/软件安全审计总览：范围界定→资产清单→风险分级→逐项验证→报告模板的分阶段流程，按需转调 secret-scan、dependency-audit、supply-chain-review、prompt-injection-review 四个专项技能。用户要求整体审计仓库、规划审计步骤或汇总多类发现出报告时用；只查密钥/依赖等单一主题时直接加载对应专项技能，不用本总览。

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.