Skill Supply Chain Audit
Use when evaluating a third-party Skill, plugin, prompt, manifest, archive, MCP integration, or repository before installing, enabling, updating, publishing, or distributing it.
Install
npx skills add sandbaseai/workbuddy-skill --skill skill-supply-chain-auditgit clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/skill-supply-chain-audit ~/.claude/skills/skill-supply-chain-auditPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Skill Supply Chain Audit Treat the target as untrusted and produce an evidence-backed disposition without executing package code by default. A clean heuristic scan is not proof of safety; label every claim `observed`, `inferred`, or `unknown`. ## Scope and output Record the target path/archive/repository, exact commit or version and hash, claimed purpose, publisher/source URL, license, intended runtime, available tools, requested permissions, data sensitivity, known-good baseline, network constraints, and dynamic-testing authorization. If provenance or version is unknown, preserve that gap rather than inferring trust from popularity. Return: 1. Scope, target identity, method, coverage, and limitations. 2. `approve`, `approve-with-constraints`, `quarantine`, or `reject`. 3. An inventory of instructions, executables, dependencies, endpoints, credentials, filesystem reach, network egress, and persistence. 4. Stable findings with severity, confidence, exact evidence, preconditions, impact, and remediation. 5. Permission constraints, safe verification plan, residual risks, and open questions. ## Safe static inspection Work read-only on a copy or immutable snapshot. Do not import modules, run setup hooks, install dependencies, render active content, follow embedded links, or invoke package tools during static review. Keep network off unless a specific provenance check is authorized. Never expose secrets; redact tokens, home
Details
- Skill name
skill-supply-chain-audit- Repository
- sandbaseai/workbuddy-skill
- Path
skills/skill-supply-chain-audit/SKILL.md- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the Skill Supply Chain Audit skill do?
Use when evaluating a third-party Skill, plugin, prompt, manifest, archive, MCP integration, or repository before installing, enabling, updating, publishing, or distributing it.
How do I install the Skill Supply Chain Audit skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill skill-supply-chain-audit. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Skill Supply Chain Audit 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.
Subagent Driven Development
9sandbaseai/workbuddy-skill
Use when executing a multi-step implementation plan with independent tasks and each task needs isolated implementation, review, and final branch verification.
Skill Sunset
9sandbaseai/workbuddy-skill
Use when cleaning up, modernizing, retiring, or evaluating accumulated AGENTS.md, CLAUDE.md, or SKILL.md instructions; produce evidence-backed, reversible recommendations without automatically deleting domain or safety knowledge.
Threat Model Analyst
9sandbaseai/workbuddy-skill
Use when explicitly asked to threat-model a repository or update an existing threat model with evidence-backed STRIDE-A findings.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.