daily-supply-chain-audit

Audit AI agent toolchains for version drift, tampering, and vulnerabilities.

6|1|Updated May 13, 2026
One-click install
npx skills add https://github.com/Xipher-Labs/walter-os --skill daily-supply-chain-audit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: daily-supply-chain-audit
Source: https://github.com/Xipher-Labs/walter-os/tree/main/skills/daily-supply-chain-audit
Command: npx skills add https://github.com/Xipher-Labs/walter-os --skill daily-supply-chain-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, node/npm, python3, mcp-scan, mcp-scanner, sha256sum/shasum, shasum, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill prevents security and supply-chain compromises in an AI agent environment by continuously auditing MCP servers, Claude/Codex tool configuration, installed skills, and package versions for drift, tampering, and known risk signals.

Core Features & Use Cases

  • Daily end-to-end supply chain audit: checks tool versions, config drift, hook integrity, installed MCP servers, and connected MCP tool definitions against baselines.
  • Pinned dependency enforcement & release-age gating: flags unpinned MCP tool version specs and detects packages published too recently for the active protection level.
  • Actionable blocking/triage gates: produces a timestamped markdown report, uses severity-based exit codes for daily gating, and supports acknowledgements and justified exceptions.
  • Secrets and script safety checks: detects plaintext-looking secrets in configs and performs static checks on skill scripts for risky patterns (e.g., unsafe shell pipelines).
  • Use cases: run every morning before work, after installing new MCP/skills, and whenever you suspect prompt injection, tool poisoning, configuration drift, or vulnerabilities.

Quick Start

Use it with this command:

indented text: walter-os skills daily-supply-chain-audit --run

Frequently Asked Questions about daily-supply-chain-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a daily supply chain security audit for my MCP servers?

Run a daily supply chain audit by executing the skill command, which validates installed MCP server versions, checks config baselines, and scans for known vulnerabilities. It generates a timestamped markdown report with severity-based exit codes for gating.

How does config drift detection work for AI agent toolchains?

Config drift detection works by deterministic baseline diffing, comparing current agent tool configurations and hook content hashes against established baselines. It identifies unauthorized changes to MCP servers, installed skills, and package versions.

Can I enforce pinned dependency versions and release-age gating for MCP tools?

Yes, you can enforce pinned dependency versions and release-age gating for MCP tools. The audit flags unpinned tool version specs and detects packages published too recently based on your active protection level to prevent supply chain risks.

Do I need node and python3 installed to perform an MCP security audit?

Yes, you need node/npm and python3 installed to perform an MCP security audit, along with jq, mcp-scan, mcp-scanner, and shasum. These dependencies enable version validation, vulnerability scanning, and package integrity checks.

What's the best way to check for plaintext secrets in MCP configurations?

The best way to check for plaintext secrets in MCP configurations is running this audit skill, which detects plaintext-looking secrets in configs and performs static checks on skill scripts for risky patterns like unsafe shell pipelines.

When should I run a supply chain audit for agent safety beyond my daily morning check?

Run a supply chain audit for agent safety beyond your daily morning check after installing new MCP servers or skills, and whenever you suspect prompt injection, tool poisoning, configuration drift, or vulnerabilities. It verifies post-install integrity.