dependency-confusion

dependency-confusion is a skill for Claude Code, Codex from yaklang/hack-skills. It costs 56 tokens per session (2,356 once invoked), scanned A, original, MIT.

A security testing playbook for dependency confusion, an attack where a package manager installs a malicious public package instead of a private internal package with the same name.

In plain words
What is it for?
Use it to review npm, pip, RubyGems, Maven, Composer, or Docker manifests; check private-package exposure and registry rules; run authorized non-destructive tests; and plan defensive controls.
Why use it?
It helps reveal cases where package resolution, registries, version ranges, or missing lockfiles could allow attacker-controlled code to run during installation or builds.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review npm, pip, RubyGems, Maven, Composer, or Docker manifests; check private-package exposure and registry rules; run authorized non-destructive tests; and plan defensive controls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yaklang/hack-skills/dependency-confusion
About the project

HackSkills is an organized knowledge base of installable skills that gives AI agents practical security knowledge across areas such as web security, privilege escalation, reverse engineering, and digital forensics. It is intended for bug bounty work, penetration testing, CTF competitions, and authorized security research. The catalogue entries are the project's own master, category, and topic skills.

yaklang/hack-skills · 2,098 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yaklang/hack-skills --skill dependency-confusion
Clone the repo
git clone --depth 1 https://github.com/yaklang/hack-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dependency-confusion

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaklang/hack-skills/dependency-confusion.svg)](https://agentmods.dev/skills/yaklang/hack-skills/dependency-confusion)
Your own site
<a href="https://agentmods.dev/skills/yaklang/hack-skills/dependency-confusion"><img src="https://agentmods.dev/badge/skills/yaklang/hack-skills/dependency-confusion.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 22 Apr 2026
  • Snyk fail 22 Apr 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.02356
Opus 5 $0.00028 $0.01178
Sonnet 5 $0.00011 $0.00471
Haiku 4.5 $0.00006 $0.00236

Measured 7d ago against content hash 8da1209f3125, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dependency-confusion scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

# curl "https://search.maven.org/solrsearch/select?q=g:com.example+AND+a:internal-lib&rows=1&wt=json"
Origin

Copies of this mod

4 near-identical copies found in the catalogue:

skills/dependency-confusion/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: Dependency Confusion — Supply Chain Attack Playbook

AI LOAD INSTRUCTION: Expert dependency-confusion methodology. Covers how private package names leak, how public registries can win version resolution, ecosystem-specific pitfalls (npm scopes, pip extra indexes, Maven repo order), recon commands, non-destructive PoC patterns (callbacks, not data exfil), and defensive controls. Pair with supply-chain recon workflows when manifests or CI caches are in scope. Only use on systems and programs you are authorized to test.

0. QUICK START

What to look for first

  • Manifests listing package names that look internal (short unscoped names, org-specific tokens, product codenames) without a hard-private registry lock.
  • Evidence the same name might exist—or be squattable—on a public registry with a higher semver than the private feed publishes.
  • Lockfiles missing, stale, or not enforced in CI so install/build can drift toward public metadata.

Fast mental model: If the resolver can see both private and public indexes, and version ranges allow it, the “newest” matching version may be the attacker’s.

Routing note: if the task comes from supply-chain, repository exposure, or CI-build recon, first use recon-for-sec to list internal package names and possible public-registry collisions.


1. CORE CONCEPT

  1. Private packages: An organization ships libraries only on an internal registry (or under conventions that imply “ours”), e.g. a scoped name like @org-scope/internal-utils or an unscoped name such as acme-billing-sdk.
  2. Attacker squats the name: The same package name is published on a public registry (npmjs, PyPI, RubyGems, etc.).
  3. Resolver preference: Many setups resolve highest matching version across all configured indexes (or merge metadata), so a public 9.9.9 can beat a private 1.2.3 if ranges allow.
  4. Execution: Package managers run lifecycle scripts (npm preinstall/postinstall, setuptools entry points, etc.) → attacker code runs on developer laptops, CI, or production image builds.

Read the full file on GitHub · 179 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 179 lines · 56 tokens per session scan A 8da1209f3125

Subscribe to this mod's changes

dependency-confusion is a skill published in the GitHub repository yaklang/hack-skills (2,098 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 2,356 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens