mcpbeat Sign in

Diagnosing Dependabot Alerts Agent Skill

Diagnoses GitHub Dependabot / security alerts in the Medusa monorepo and finds the least-invasive fix. Use when investigating a Dependabot alert, security advisory (GHSA/CVE), vulnerable dependency, "npm audit" finding, or a security update PR. Traces the vulnerable package to the exact affected workspace package(s) under packages/, assesses real impact, and prefers a fix scoped to the affected package over a root package.json / yarn.lock resolutions override (which is a last resort).

4k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
35569
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/medusajs/medusa --skill diagnosing-dependabot-alerts

What comes with it

7 145 bytes besides the instruction
reference/remediation-strategies.md

The instruction itself

10 sections, as written by the author

Diagnosing Dependabot Alerts

Investigate a Dependabot/security alert in the Medusa monorepo, identify the exact affected package(s), assess real-world impact, and pick the least-invasive fix. Default output is a diagnosis; only make changes when asked.

Constraints

  • Diagnose first, don't default to a fix: Never jump to a root resolutions/overrides bump. Root-level overrides are the LAST resort — see the remediation ladder.
  • Root overrides don't ship: resolutions (yarn) / overrides (npm) apply only to THIS repo's install. They are NOT published with packages/*, so they do not protect downstream consumers of a published package. Never present them as a full fix for a vulnerability that reaches a published package.
  • Find the fix inside the affected package first: Prefer refreshing/bumping the dependency within the workspace package that owns it (transitive refresh or direct-dep bump) before touching anything at the monorepo root.
  • Reachable is not pinnable: A fixed version being resolvable within existing semver ranges (a lockfile float) is weaker than a range that GUARANTEES the fix. Call out the difference — the float can regress for downstream consumers.
  • Assess impact, don't assume: Determine whether the vulnerable code path is actually reachable with untrusted input in Medusa before recommending urgency.

Workflow

Follow these steps in order. Load reference/remediation-strategies.md before proposing any fix.

1. Fetch alert details        → gh api (package, versions, scope)
2. Trace to affected package  → walk yarn.lock up to packages/*
3. Assess real impact         → is the vulnerable path reachable?
4. Choose remediation         → remediation ladder (least-invasive first)
5. Verify (only if changing)  → scoped diff, no vulnerable version remains

1. Fetch alert details

The alert number is the last path segment of the URL (.../dependabot/<N>).

gh api repos/medusajs/medusa/dependabot/alerts/<N> | jq '{
  state, package: .dependency.package.name, scope: .dependency.scope,
  relationship: .dependency.relationship, manifest: .dependency.manifest_path,
  ghsa: .security_advisory.ghsa_id, severity: .security_advisory.severity,
  summary: .security_advisory.summary,
  matched_range: .security_vulnerability.vulnerable_version_range,
  first_patched: .security_vulnerability.first_patched_version.identifier,
  all_ranges: [.security_advisory.vulnerabilities[] | {range: .vulnerable_version_range, patched: .first_patched_version.identifier}]
}'

Record: the vulnerable package name, every {vulnerable range → first patched} pair, and whether the alert is direct or transitive.

2. Trace to the exact affected Medusa package(s)

Find which version(s) are actually installed and walk up the dependency chain to the workspace package(s) under packages/ that own the dependency. See reference/remediation-strategies.md for the full tracing recipe. In short:

  • grep -n "<pkg>@npm" yarn.lock — list installed versions; confirm which match the vulnerable range.
  • Walk up dependents (grep the version string as a dependency of other lock entries) until you reach a package declared in a packages/*/package.json.
  • For that workspace package, determine:
  • Direct vs transitive — is <pkg> (or the nearest ancestor) in its dependencies/devDependencies, or purely transitive?
  • Ships or notprivate: false means it publishes; a runtime dependencies entry ships to consumers. devDependencies and private: true do not.
  • Runtime-reachable — is the ancestor actually imported in src/ (runtime), or only used at build/test time?

The "affected package" is the workspace package whose manifest declares the dependency (or the nearest ancestor that does).

3. Assess real impact

Before recommending urgency, check whether the vulnerable code path is reachable with untrusted input in Medusa. Example from a past alert: immutable prototype pollution reached us only through @graphql-codegen/typescript, used to generate types from Medusa's OWN internal GraphQL schema — no untrusted input, so practical exploitability was negligible. State the impact explicitly; it changes how aggressive the fix needs to be.

4. Choose remediation (least-invasive first)

Load reference/remediation-strategies.md now. Apply the ladder in order and stop at the first tier that works without breaking changes:

| Tier | Fix | Scope | Ships to consumers? |

|------|-----|-------|---------------------|

| 1a | In-range transitive refresh (lockfile only) | affected pkg's tree | reflects fresh installs |

| 1b | Bump the direct dep the affected pkg declares | affected pkg's package.json | yes (enforced) |

| 2 | Root resolutions/overrides | this repo only | NO — last resort |

  • Prefer 1a when a fixed version is reachable within existing ranges and introduces no breaking changes (fastest, no manifest change).
  • Use 1b when the fix is only *guaranteed* by bumping the declared dep — check breaking changes (major bump, peerDeps, changed API usage) per the reference file.
  • Use 2 only when no in-package option exists; always state that it does not protect downstream consumers of published packages.

5. Verify (only when making changes)

  • git diff --stat — confirm the change is scoped (only yarn.lock, plus package.json if you bumped a direct dep).
  • Confirm NO version matching the vulnerable range remains in yarn.lock.
  • Confirm the diff touches only the vulnerable package's dependency neighborhood — no unrelated churn.
  • If a direct dep was bumped: build/typecheck the affected package and exercise its use of the dependency.

Reference Files Available

reference/remediation-strategies.md  - Tracing recipe, semver reachable-vs-pinnable
                                        analysis, per-tier commands, breaking-change checks

Common Mistakes Checklist

Verify you're NOT doing these:

  • [ ] Adding a root resolutions/overrides entry as the first (or only) fix
  • [ ] Presenting a root override as protecting downstream consumers of a published package
  • [ ] Treating a lockfile float ("reachable") as a guaranteed fix ("pinnable")
  • [ ] Skipping the trace and not naming the exact affected packages/* package(s)
  • [ ] Recommending a major-version bump without checking breaking changes / peerDeps / actual usage
  • [ ] Reporting urgency without checking whether the vulnerable path is reachable in Medusa
  • [ ] Making changes when only a diagnosis was requested

Other skills for the same job

different authors, same section of the catalogue
Codebase Cleanup Deps Audit
by ComeOnOliver
×2

You are a dependency security expert specializing in vulnerability scanning, license compliance, and supply chain security. Analyze project dependencies for known vulnerabilities, licensing issues, outdated packages, and provide actionable remediation strategies.

10k tokens
Security Best Practices
by openai
vendor ×1

Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.

103k tokens
Better Auth
by mrgoonie
×1

Implement authentication and authorization with Better Auth - a framework-agnostic TypeScript authentication framework. Features include email/password authentication with verification, OAuth providers (Google, GitHub, Discord, etc.), two-factor authentication (TOTP, SMS), passkeys/WebAuthn support, session management, role-based access control (RBAC), rate limiting, and database adapters. Use when adding authentication to applications, implementing OAuth flows, setting up 2FA/MFA, managing user sessions, configuring authorization rules, or building secure authentication systems for web applications.

46k tokens scripts
Repomix
by mrgoonie
×1

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

27k tokens scripts
Dependency Management Deps Audit
by lingxling
×1

You are a dependency security expert specializing in vulnerability scanning, license compliance, and supply chain security. Analyze project dependencies for known vulnerabilities, licensing issues, outdated packages, and provide actionable remediation strategies.

7k tokens
Hubspot Integration
by lingxling
×1

Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers Node.js and Python SDKs.

5k tokens
Security Best Practices
by christophacham
×1

Perform language and framework specific security best-practice reviews and suggest improvements. Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help. Supports Python, JavaScript/TypeScript, and Go. Do NOT use for general code review, debugging, threat modeling (use security-threat-model), or non-security tasks.

102k tokens
API Gateway Configuration
by ComeOnOliver
×1

Configures API gateways for routing, authentication, rate limiting, and request transformation in microservice architectures. Use when setting up Kong, Nginx, AWS API Gateway, or Traefik for centralized API management.

525 tokens

How to use it

Copy the folder

Take medusajs/diagnosing-dependabot-alerts from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.