Ring:Auditing Dependency Security logo

Ring:Auditing Dependency Security

Organization
LerianStudio
ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a dependency PR, or investigating a compromise. Skip when no new dependency is involved or it is already vetted.

Overview

PublisherLerianStudio
Repositoryring
Skill namering:auditing-dependency-security
Stars
215
Forks
28
Bundled files
Instructions only
LicenseApache-2.0
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 LerianStudio on GitHub. Read the source before you install it.

Installation

Install the Ring:Auditing Dependency Security 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/LerianStudio/ring.git /tmp/ring
mkdir -p .claude/skills
cp -r /tmp/ring/dev-team/skills/auditing-dependency-security .claude/skills/lerianstudio-ring-auditing-dependency-security
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ring:Auditing Dependency Security 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 Ring:Auditing Dependency Security 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 Ring:Auditing Dependency Security 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 Security Check

When to use

  • Adding a new dependency to any project
  • Running pip install, npm install, go get, or equivalent
  • Auditing existing dependencies for supply-chain risk
  • Reviewing a PR that adds or updates dependencies
  • Investigating a potential supply-chain compromise

Skip when

  • No dependencies are being added, updated, or audited
  • Task involves only internal code changes with no new imports
  • Dependency is already vetted and pinned in lockfile

Related

Complementary: ring:hardening-dockerfiles, ring:implementing-tasks

Supply-chain gate for every install command in a Lerian codebase.

Pre-Install Checks

1. Package Identity Verification

For every package, verify:
├── Typosquatting: compare against known popular packages
│   e.g., "requets" vs "requests", "rnodule" vs "module"
├── Homoglyph attacks: look-alike Unicode characters
├── Maintainer risk:
│   - Single maintainer = higher risk
│   - Account age < 6 months = flag
│   - Recent ownership transfer = CRITICAL flag
└── Package age: < 30 days = flag

2. Vulnerability Database Check

SourceEcosystemWhat It Covers
OSV.devAllGoogle aggregated CVEs
GitHub Advisory DatabaseAllGHSA linked to CVEs
Socket.devnpm, pipSupply-chain: install scripts, network access
PyPI JSON APIpipMetadata, maintainers, release history
npm registry APInpmMetadata, maintainers, install scripts
Go vulnerability DB (vuln.go.dev)GoOfficial Go CVE database

3. Behavioral Signals

SignalRisk LevelDescription
Install scriptsHIGHpostinstall (npm), setup.py subprocess
Network access at importCRITICALPackage phones home on import
File system access outside projectHIGHReads ~/.ssh, ~/.aws, env vars
Obfuscated codeCRITICALBase64 payloads, eval(), exec()
Native binary bundledHIGHPre-compiled binaries without source

4. Lockfile Integrity

EcosystemLockfileHash Requirement
Gogo.sumSHA-256 native — Go handles automatically
npmpackage-lock.jsonintegrity field (SHA-512) must be present for ALL deps
piprequirements.txt--require-hashes MUST be enforced
CargoCargo.lockchecksum field verification

Risk Scoring

risk_score = weighted_sum(
  typosquatting_similarity * 25,
  maintainer_risk          * 20,
  package_age_risk         * 15,
  vulnerability_count      * 20,  # weighted by severity
  behavioral_flags         * 15,
  lockfile_integrity       * 5
)

Score thresholds:

  • 0-25: LOW — proceed
  • 26-50: MEDIUM — proceed with documentation
  • 51-75: HIGH — escalate to Fred before installing
  • 76-100: CRITICAL — block installation

Decision Matrix

Risk LevelAction
LOW (0-25)✅ Approve — document in PR
MEDIUM (26-50)⚠️ Conditional — mitigations required
HIGH (51-75)🚨 Escalate to Fred before installing
CRITICAL (76-100)❌ Block — do not install

Report Template

markdown
## Dependency Security Report

Package: {name} @ {version}
Ecosystem: {go|npm|pip}
Risk Score: {score}/100 — {LOW|MEDIUM|HIGH|CRITICAL}

### Verification Results

| Check | Status | Details |
|-------|--------|---------|
| Typosquatting check | PASS/FLAG | {comparison} |
| Maintainer verification | PASS/FLAG | {maintainer count, age} |
| Vulnerability scan | PASS/FLAG | {CVE count, severity} |
| Behavioral analysis | PASS/FLAG | {signals found} |
| Lockfile integrity | PASS/FAIL | {hash present/missing} |

### Decision
{APPROVED|CONDITIONAL|ESCALATE|BLOCKED}

### Required Actions (if not APPROVED)
1. {specific mitigations or alternatives}

Mitigations for MEDIUM Risk

  • Pin exact version in lockfile
  • Vendor the dependency (copy source into repo)
  • Document why this specific package was chosen over alternatives
  • Add to security monitoring (e.g., GitHub Dependabot alerts)

Frequently asked questions

What does the Ring:Auditing Dependency Security AI skill do?

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a dependency PR, or investigating a compromise. Skip when no new dependency is involved or it is already vetted.

Why use Ring:Auditing Dependency Security on TypingMind?

Because you install it once and use it with any model. Ring:Auditing Dependency Security 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 Ring:Auditing Dependency Security in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LerianStudio/ring/tree/main/dev-team/skills/auditing-dependency-security. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ring:Auditing Dependency Security?

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 Ring:Auditing Dependency Security?

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

Is the Ring:Auditing Dependency Security AI skill free?

Yes. It is published on GitHub by LerianStudio under the Apache-2.0 license. 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 👇