Agent Supply Chain
Use when generating or verifying integrity manifests, auditing dependency pinning, detecting tampered agent plugins or tools, or establishing provenance gates for agent-component promotion.
Install
npx skills add sandbaseai/workbuddy-skill --skill agent-supply-chaingit clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/agent-supply-chain ~/.claude/skills/agent-supply-chainPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Agent Supply Chain Integrity 审查 Agent 插件、工具包、MCP 组件和其依赖的完整性与来源。通过确定性文件清单、精确版本审计、来源链和晋级门禁,发现篡改、漂移、未登记文件和不可复现的构建输入。 ## 安全边界 - 默认只读:扫描目标、读取配置、计算哈希、比较已批准清单并生成报告。 - 不执行被审查的脚本、安装依赖、访问网络、签署制品、修改注册表或晋级环境。 - 目标目录、基线清单、提交/制品标识和信任策略必须明确;缺失时标记为 `unknown`,不得猜测。 - 完整性证明不等于代码安全。仍需审查权限、网络、凭据、动态执行和依赖行为。 - 清单与报告不得包含密钥、令牌、私有路径中的敏感名称或用户数据。 ## 完整性清单 为组件生成确定性清单时: 1. 固定根目录和允许的文件类型;排除 `.git`、缓存、虚拟环境、依赖下载目录及清单自身,并记录排除规则。 2. 按规范化的相对 POSIX 路径排序,使用 SHA-256 分块读取文件;不跟随根目录外的符号链接。 3. 保存 `component_name`、`source_revision`、`algorithm`、`file_count`、`files`、`generated_at` 和清单链哈希。 4. 将来源仓库、提交 SHA、构建器、锁文件、构建时间和制品摘要作为 provenance 字段;未知字段明确标注。 清单链哈希应由排序后的路径及其文件哈希稳定计算。时间戳不得参与内容链哈希,否则同一内容无法复现。 ## 核验与漂移分类 核验时先验证清单格式、算法和来源,再计算当前文件集合。分别报告: - `MISSING`:基线登记但当前缺失; - `MODIFIED`:路径存在但哈希不一致; - `UNTRACKED`:当前存在但未登记; - `OUT_OF_SCOPE`:链接或文件越过批准根目录; - `BASELINE_UNKNOWN`:没有可信、固定版本的比较基线。 任何缺失、修改、未登记或越界项都使核验失败;不要用“文件数量相同”替代逐文件比较。生成报告时同时给出基线来源、扫描范围、排除项、错误列表和可复核命令。 ## 依赖与版本审计 检查 `package.json`、锁文件、`requirements.txt`、`pyproject.toml`、容器清单和 Agent 配置: - 标记 `latest`、`*`、浮动 `^`/`~`、无上界范围和未锁定 Git 引用; - 优先以 lockfile、发布制品摘要或提交 SHA 作为可复现依据; - 将直接依赖、传递依赖、构建工具和运行时插件分开统计; - 记录弃用、来源切换、维护者变化、权限扩张和新增安装脚本等升级风险; - 不因为版本已锁定就断言无漏洞,漏洞与许可证判断需独立证据。 ## 来源链与晋级门禁 在 `dev → staging → production` 或发布前,至少核对: 1. 源代码提交、构建输入、锁文件和制品摘要相互一致。 2. 构建结果与已审查清单逐文件匹配,且清单由批准的 CI 身份生成。 3. 签名、证明或不可用状态被明确记录;不能验证签名时 fail closed,不得改写状态为 verified。 4. 晋级范围、批准人/策略、时间、环境和回滚制品可追溯。 5. 任何重建、依赖变化、权限变化或基线更新都触发重新审查。 ## 交付报告
Details
- Skill name
agent-supply-chain- Repository
- sandbaseai/workbuddy-skill
- Path
skills/agent-supply-chain/SKILL.md- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the Agent Supply Chain skill do?
Use when generating or verifying integrity manifests, auditing dependency pinning, detecting tampered agent plugins or tools, or establishing provenance gates for agent-component promotion.
How do I install the Agent Supply Chain skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill agent-supply-chain. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agent Supply Chain popular?
It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.
Related skills
Access Control Security Best Practices
9sandbaseai/workbuddy-skill
Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.
Accessibility Review
9sandbaseai/workbuddy-skill
Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.
Acquire Codebase Knowledge
9sandbaseai/workbuddy-skill
Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.
Agentic Evaluation
9sandbaseai/workbuddy-skill
Use when measuring or improving an Agent's output with explicit criteria, reflection, evaluator-optimizer loops, rubric or judge comparisons, code-test refinement, and bounded convergence checks.
Agent Skill Stack
9sandbaseai/workbuddy-skill
Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has low Skill recall, wants indirect helpers such as humanizers or compliance checks, or wants a project-specific Skill Stack with controlled installation. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit, safety, and overlap. Do not use for locating one known or common Skill; use the generic find-skills wo
AI Governance
9sandbaseai/workbuddy-skill
Use when classifying AI-system risk, establishing responsible-AI governance, preparing model or system documentation, assessing human oversight, or mapping controls to frameworks such as the EU AI Act and NIST AI RMF.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.