Reviewing Dependencies logo

Reviewing Dependencies

Organization
bitwarden
reviewing-dependencies

This skill should be used when the user asks to "review Dependabot alerts", "check for vulnerable dependencies", "audit third-party packages", "assess supply chain risk", "run an Aikido scan", or needs to evaluate dependency health, transitive risk, or supply chain security.

Overview

Publisherbitwarden
Repositoryai-plugins
Skill namereviewing-dependencies
Stars
149
Forks
19
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bitwarden on GitHub. Read the source before you install it.

Installation

Install the Reviewing Dependencies AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bitwarden/ai-plugins.git /tmp/ai-plugins
mkdir -p .claude/skills
cp -r /tmp/ai-plugins/plugins/bitwarden-security-engineer/skills/reviewing-dependencies .claude/skills/reviewing-dependencies
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Reviewing Dependencies in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Reviewing Dependencies on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Reviewing Dependencies is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dependency Vulnerability Workflow

Step 1: Gather Alerts

bash
# List all open Dependabot alerts sorted by severity
gh api /repos/{owner}/{repo}/dependabot/alerts --jq '.[] | select(.state == "open") | {number, severity: .security_vulnerability.severity, package: .security_vulnerability.package.name, ecosystem: .security_vulnerability.package.ecosystem, summary: .security_advisory.summary}'

# Filter by severity
gh api "/repos/{owner}/{repo}/dependabot/alerts?severity=critical&state=open"

# Get full details for a specific alert
gh api /repos/{owner}/{repo}/dependabot/alerts/{alert_number}

Step 2: Assess Impact

For each alert, determine:

  1. Is the vulnerable code path reachable? — Does the application actually use the vulnerable function/feature of the dependency?
  2. Is it a direct or transitive dependency? — Transitive vulnerabilities may be harder to fix but still pose real risk.
  3. What is the CVSS score and exploit availability? (Score with the CVSS convention triaging-security-findings defines for effective severity.) A high CVSS with a public exploit needs immediate action. A medium CVSS with no known exploit can be scheduled.
  4. What versions are affected and what versions fix it? — Check if updating is a minor bump or a breaking change.

Step 3: Decide on Action

SituationAction
Fix available, minor version bumpUpdate immediately
Fix available, major version bumpEvaluate breaking changes, schedule update
No fix available, code path reachableImplement workaround or replace dependency
No fix available, code path not reachableDocument and monitor, set review date
Vulnerability in transitive dependencyUse overrides/resolutions to pin fixed version

Transitive Dependency Risk

Direct dependencies are visible in package.json or .csproj files, but transitive dependencies (dependencies of dependencies) make up the majority of the dependency tree and are often invisible.

Why transitive dependencies matter:

  • A vulnerability in a deeply nested dependency is just as exploitable as one in a direct dependency
  • Transitive dependencies are less likely to be actively monitored
  • Updating a transitive dependency may require updating the direct dependency that pulls it in

How to investigate:

bash
# npm: Show full dependency tree
npm ls --all

# npm: Find which direct dependency pulls in a vulnerable transitive
npm ls <vulnerable-package>

# .NET: List all vulnerable packages including transitive
dotnet list package --vulnerable --include-transitive

# .NET: Show dependency graph
dotnet list package --include-transitive

Dependency Health Evaluation

When evaluating whether to adopt or keep a dependency, assess:

CriterionGreen FlagRed Flag
MaintenanceRegular commits, responsive to issuesNo commits in 12+ months, unresponded issues
Vulnerability HistoryFew CVEs, quick patchesRepeated CVEs, slow response
Maintainer CountMultiple active maintainersSingle maintainer, bus factor of 1
CommunityHigh download count, active usersVery low adoption for claimed scope
LicenseCompatible with project (MIT, Apache-2.0)Restrictive or ambiguous license
Security PracticesSigned releases, security policy, 2FANo security policy, no signed releases

Aikido Integration

Aikido is Bitwarden's container and open-source dependency scanner. It continuously scans connected repositories, surfacing open-source (SCA) and container findings in the same feed as SAST, IaC, and secrets results.

Use the aikido:issues skill (aikido_issues_list) to query findings, scoping to the relevant repo and filtering issue_types to open_source (dependency CVEs) and docker_container (container image vulnerabilities). cloud_instance is a separate Aikido issue type for cloud VM/instance findings — out of scope for dependency and container review.

Use the caller-supplied Aikido evidence if you were given any. Otherwise query aikido:issues, and if it is unavailable, stop and tell the user rather than proceeding without this data.

bash
# Use the aikido:issues skill, e.g.:
# issue_types: ["open_source"], repo_name: "<repo>"       -> dependency CVEs
# issue_types: ["docker_container"], repo_name: "<repo>"  -> container image vulnerabilities

Interpreting Aikido output:

  • Each finding includes: issue title, type, severity (and severity label), remediation guidance, and SLA due date
  • Use out_of_sla: true to focus on findings already past their remediation SLA
  • Triage follows the same Jira-based flow as other Aikido findings — see the triaging-security-findings skill

Platform-Specific Guidance

NuGet (.NET)

bash
# Check for vulnerable packages
dotnet list package --vulnerable

# Include transitive dependencies
dotnet list package --vulnerable --include-transitive

# Check for outdated packages
dotnet list package --outdated

NuGet-specific concerns:

  • .NET framework packages may have different vulnerability profiles than .NET Core
  • PackageReference in .csproj is preferred over packages.config for better transitive resolution
  • Use Directory.Packages.props for centralized version management in multi-project solutions

npm (Node.js)

bash
# Run security audit
npm audit

# Auto-fix where possible
npm audit fix

# Force fixes (may introduce breaking changes)
npm audit fix --force

# Check lockfile integrity
npm ci  # Installs exactly from lockfile, fails if lockfile is out of date

npm-specific concerns:

  • package-lock.json must be committed and kept in sync
  • Use overrides in package.json to force transitive dependency versions:
    json
    {
      "overrides": {
        "vulnerable-package": ">=2.0.0"
      }
    }
  • Beware of postinstall scripts in dependencies — they execute arbitrary code during npm install

SBOM Concepts

A Software Bill of Materials (SBOM) is an inventory of all components in a software artifact. Understanding SBOMs helps reason about supply chain risk:

  • What it contains: Package names, versions, licenses, relationships (direct vs. transitive)
  • Why it matters: Enables rapid response when a new CVE is published — immediately identify which projects are affected
  • Standard formats: SPDX, CycloneDX
  • GitHub integration: GitHub generates dependency graphs automatically; Dependabot uses this for alerting

Critical Rules

  • Never ignore critical/high Dependabot alerts without documented justification. Even if the vulnerable code path seems unreachable, document why.
  • Prefer updating over pinning. Pinning a vulnerable version and adding a workaround accumulates tech debt. Update when a fix is available.
  • Evaluate the full transitive tree. A direct dependency may be safe, but its transitive dependencies may not be.
  • Review new dependencies before adoption. Check health criteria above before adding any new package. More dependencies = more attack surface.
  • Lock dependencies. Always commit lockfiles (package-lock.json, packages.lock.json). Use npm ci in CI/CD, not npm install.

Frequently asked questions

What does the Reviewing Dependencies AI skill do?

This skill should be used when the user asks to "review Dependabot alerts", "check for vulnerable dependencies", "audit third-party packages", "assess supply chain risk", "run an Aikido scan", or needs to evaluate dependency health, transitive risk, or supply chain security.

Why use Reviewing Dependencies on TypingMind?

Because you install it once and use it with any model. Reviewing Dependencies is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Reviewing Dependencies in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwarden/ai-plugins/tree/main/plugins/bitwarden-security-engineer/skills/reviewing-dependencies. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Reviewing Dependencies?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Reviewing Dependencies?

As many as you like. As long as a model supports skills, you can use Reviewing Dependencies with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Reviewing Dependencies AI skill free?

It is published on GitHub by bitwarden. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇