detecting-malicious-npm-packages

detecting-malicious-npm-packages is a skill for Claude Code, Codex from adriannoes/awesome-agentic-ai. It costs 27 tokens per session (2,398 once invoked), scanned A, original, MIT.

A security triage guide for examining npm packages, which are reusable JavaScript components, for malware that runs during installation or package use.

In plain words
What is it for?
Use it to inspect suspicious packages for installation-script malware, data theft, and self-spreading behavior in an isolated environment.
Why use it?
It helps prevent a dangerous package from compromising a developer's machine or software supply chain.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is guarddog npm scan ./package/.

Good fit Use it to inspect suspicious packages for installation-script malware, data theft, and self-spreading behavior in an isolated environment.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai
agentmods
npx agentmods add skills/adriannoes/awesome-agentic-ai/detecting-malicious-npm-packages

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 detecting-malicious-npm-packages

README.md
[![agentmods](https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/detecting-malicious-npm-packages/github.svg)](https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/detecting-malicious-npm-packages)
Your own site
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/detecting-malicious-npm-packages"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/detecting-malicious-npm-packages/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for detecting-malicious-npm-packages

Your own site · 80×15
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/detecting-malicious-npm-packages"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/detecting-malicious-npm-packages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 31
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 75
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Excessive Agency · line 29
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium MCP Rug Pull · line 50
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium MCP Rug Pull · line 51
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • low Tool Misuse · line 51
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 $0.00027 $0.02398
Opus 5 $0.00014 $0.01199
Sonnet 5 $0.00005 $0.00480
Haiku 4.5 $0.00003 $0.00240

Measured 9d ago against content hash a1537f89b6a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

detecting-malicious-npm-packages scanned grade A with 2 findings 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agent.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 -sL "$(npm view [email protected] dist.tarball)" -o some-pkg.tgz

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

grep -rEn "child_process|exec\(|spawn|eval\(|Buffer\.from\(.*base64|process\.env|https?://" package/ \
cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/detecting-malicious-npm-packages/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detecting Malicious npm Packages

Legal Notice: Analyze packages in an isolated, disposable environment. Some malicious packages execute on install (npm install runs lifecycle scripts automatically) or on import. Never analyze a suspect package on a workstation with credentials, SSH keys, cloud tokens, or network access to production. This skill is for defensive analysis and authorized incident response only.

Overview

The npm registry is the largest software package ecosystem in the world and the most heavily targeted by supply-chain attackers. Malicious packages reach victims through typosquatting (expresss, crossenv), dependency confusion, account/maintainer takeover (the 2025 Shai-Hulud worm and the event-stream compromise are canonical examples), and starjacking. The defining danger of npm is that npm install automatically runs preinstall, install, and postinstall lifecycle scripts with the developer's full privileges before any application code is invoked — so simply installing a package is enough to be compromised. Roughly 2% of npm packages use install scripts, which makes them both common and a powerful malware delivery vehicle.

Typical malicious behaviors are: exfiltrating environment variables, ~/.npmrc tokens, SSH keys, and cloud credentials to an attacker-controlled URL; opening reverse shells; dropping cryptominers; reading and posting process.env; obfuscating payloads with base64/eval; and self-propagating (worming) by stealing the maintainer's npm token and republishing trojanized versions of other packages they own.

This skill provides a repeatable triage workflow centered on GuardDog (Datadog's open-source heuristic scanner built on Semgrep + metadata rules), supplemented by manual tarball inspection, lockfile-based compromise checks against known-bad version lists, and dynamic detonation with network and filesystem monitoring. The goal is to decide, quickly and safely, whether a given package or a project's dependency tree contains malicious code.

Read the full file on GitHub · 200 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 200 lines · 27 tokens per session scan A a1537f89b6a9

Subscribe to this mod's changes

detecting-malicious-npm-packages is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 27 tokens to every session and 2,398 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

php

Use when writing, reviewing or modernizing PHP (8.3-8.5) outside Laravel — strict types, union and intersection types, readonly classes, backed enums, property hooks and asymmetric visibility, the pipe operator and clone-with, Composer with PSR-4, PER-CS style, PSR interop, and the quality toolchain (PHPStan, Pint…

ericrisco/rsc-harness · 97 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.

marysatasselshaped667/skills-collection-1 · 43 tokens

analyzing-dns-logs-for-exfiltration

Analyzes DNS query logs to detect data exfiltration via DNS tunneling, DGA domain communication, and covert C2 channels using entropy analysis, query volume anomalies, and subdomain length detection in SIEM platforms. Use when SOC teams need to identify DNS-based threats that bypass traditional network security…

marysatasselshaped667/skills-collection-1 · 73 tokens

analyzing-dns-logs-for-exfiltration

Analyzes DNS query logs to detect data exfiltration via DNS tunneling, DGA domain communication, and covert C2 channels using entropy analysis, query volume anomalies, and subdomain length detection in SIEM platforms. Use when SOC teams need to identify DNS-based threats that bypass traditional network security…

mukul975/Anthropic-Cybersecurity-Skills · 73 tokens

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens

writing-workflow-skills

Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

JetBrains/thinkrail · 60 tokens