Claude Marketplaces
SkillsMCP serversMarketplacesPluginsDigestAdvertise
Submit

LLMond Highlights

This week in Claude is LLMond Highlights now. A weekly email, free.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Plugins
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index
  • Plugin index

Site

  • About
  • Submit
  • Advertise
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
by Mert Düzgün
Skills/Testing & QA
yaklang avatar

Dependency Confusion

yaklang/hack-skills

This teaches Claude how to identify and test dependency confusion vulnerabilities across npm, pip, Maven, RubyGems, and other package ecosystems. It walks through the core mechanic (attacker publishes a higher version of an internal package name on a public registry), shows recon commands to check if names are squattable, and provides PoC patterns using DNS callbacks instead of destructive payloads. The guidance is red-team focused but includes defensive controls like scoped packages and lockfile enforcement. Load this when you're auditing manifests for supply chain risk or running authorized exercises against build pipelines. It pairs well with the recon-for-sec skill for initial package enumeration.

skills.sh installs
3.8K
GitHub stars
2.6K
last updated
Aug 21, 2026
View on GitHubSave

Install

$ npx -y skills add yaklang/hack-skills --skill dependency-confusion --agent claude-code

Installs into .claude/skills of the current project.

Files

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.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/yaklang/hack-skills
Categories
Testing & QA, DevOps & CI/CD, Git & Pull Requests, Code Review & Quality, Automation & Workflows, Python, Java & JVM, PHP & Laravel
First seen
Jun 3, 2026

More from yaklang/hack-skills

All 102
  • Expression Language Injection3.8K
  • Csv Formula Injection3.8K
  • Active Directory Acl Abuse3.8K
  • Linux Privilege Escalation3.8K
  • Clickjacking3.8K
  • Active Directory Kerberos Attacks3.8K
  • Jndi Injection3.8K
  • Http2 Specific Attacks3.8K
  • Saml Sso Assertion Attacks3.8K
  • Arbitrary Write To Rce3.8K
  • Active Directory Certificate Services3.8K
  • Hash Attack Techniques3.8K
  • Prototype Pollution3.8K
  • Dns Rebinding Attacks3.8K
  • Network Protocol Attacks3.8K
  • Ai Ml Security3.8K
  • Memory Forensics Volatility3.8K
  • Dangling Markup Injection3.8K
  • Windows Av Evasion3.8K
  • Defi Attack Patterns3.8K
  • Windows Privilege Escalation3.8K
  • Email Header Injection3.8K
  • Xslt Injection3.8K
  • Type Juggling3.8K

Recommended

More Testing & QA
1forcedotcom avatardeveloping-agentforceforcedotcom/sf-skillsBuild, modify, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, modifies, or asks about .agent files or aiAuthoringBundle meta3.8Kskills.sh installs
2yaklang avatarclickjackingyaklang/hack-skillsClickjacking playbook. Use when testing whether target pages can be framed, whether X-Frame-Options or CSP frame-ancestors are properly configured, and whether 3.8Kskills.sh installs
3hashicorp avatarrun-acceptance-testshashicorp/agent-skillsGuide for running acceptance tests for a Terraform provider. Use this when asked to run an acceptance test or to run a test with the prefix `TestAcc`.3.8Kskills.sh installs
4yaklang avatarsaml-sso-assertion-attacksyaklang/hack-skillsSAML SSO assertion attack playbook. Use when testing signature validation, assertion wrapping, audience restrictions, ACS handling, XML trust boundaries, and en3.8Kskills.sh installs
5yaklang avatarhash-attack-techniquesyaklang/hack-skillsHash attack playbook. Use when exploiting length extension, MD5/SHA1 collisions, HMAC timing leaks, birthday attacks, or hash-based proof of work in CTF and aut3.8Kskills.sh installs
6yaklang avatarprototype-pollutionyaklang/hack-skillsPrototype pollution testing for JavaScript stacks. Use when user input is merged into objects (query parsers, JSON bodies, deep assign), when configuring librar3.8Kskills.sh installs