inspect-malicious-code

A static-analysis procedure for checking a project or dependency for potentially malicious code such as malware or spyware. Static analysis reads code without running it.

In plain words
What is it for?
Use it to inspect obfuscation, encoded data, unexpected network access, and other suspicious patterns, with or without including node_modules.
Why use it?
It helps identify suspicious behavior while avoiding the risk of executing harmful project code.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/aiya000/dotfiles/inspect-malicious-code
Any agent
npx skills add aiya000/dotfiles --skill inspect-malicious-code
Clone the repo
git clone --depth 1 https://github.com/aiya000/dotfiles

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. Scan, not verified.
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 $0.00042 $0.00977
Opus 5 $0.00021 $0.00489
Sonnet 5 $0.00008 $0.00195
Haiku 4.5 $0.00004 $0.00098

Measured 2d ago against content hash 71da2a29746e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

inspect-malicious-code 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 2d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

> **⚠️ CRITICAL: NEVER execute any code during inspection.**

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Runs shell commandslowCapability

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

- `child_process` usage (especially `exec`, `spawn` with shell commands)
.claude_global/skills/inspect-malicious-code/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

inspect-malicious-code

Inspect a project for potentially malicious code (malware, spyware, etc.).

Arguments

  • Target directory path (optional). If not specified, use current working directory
  • --include-node-modules: Include node_modules directory in inspection (excluded by default)

Behavior

⚠️ CRITICAL: NEVER execute any code during inspection.

This skill performs static analysis only. Do not run, eval, or execute any scripts, commands, or code found in the target project. Malicious code may activate upon execution.

Step 1: Confirmation

  1. Display the target directory path clearly
  2. Ask the user: "Do you want to inspect this project for malicious code?"
  3. If yes → proceed to inspection
  4. If no → exit

Step 2: Inspection

Thoroughly examine the codebase for the following suspicious patterns:

2.1 Obfuscated Code
  • eval() usage with dynamic strings
  • Function() constructor with string arguments
  • Base64 encoded strings (especially long ones)
  • Hex-encoded strings
  • String concatenation tricks to hide keywords
  • Minified code in source files (not build artifacts)
2.2 External Communication
  • fetch() calls to unknown/suspicious URLs
  • XMLHttpRequest usage
  • http/https module imports with outbound requests
  • WebSocket connections
  • DNS lookups to suspicious domains
  • Data exfiltration patterns (sending local data externally)
2.3 Environment & Credentials Access
  • process.env access (especially for sensitive keys like API_KEY, SECRET, TOKEN, PASSWORD)
  • Reading .env files directly
  • Accessing system environment variables
  • Keychain/credential store access
  • SSH key access (~/.ssh/)
2.4 File System Access
  • Reading sensitive files (/etc/passwd, ~/.bashrc, ~/.zshrc, browser data directories)
  • Writing to system directories
  • Recursive directory scanning
  • File upload to external servers
  • Archive creation of user data
2.5 Process & System Manipulation
  • child_process usage (especially exec, spawn with shell commands)
  • Modifying PATH or other environment variables
  • Installing global packages silently
  • Modifying system configuration files
  • Persistence mechanisms (cron jobs, startup scripts)

Read the full file on GitHub · 150 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. 2d ago First seen · 150 lines · 42 tokens per session scan A 71da2a29746e

Subscribe to this mod's changes

inspect-malicious-code is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 977 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (unrestricted tool access, runs shell commands). 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

coding

Principles for writing and designing code, covering API and abstraction design, naming, comment discipline, and standards of evidence for claims about code behavior. Use whenever the task is to write or modify code, design an API or software architecture, or review code.

ryota2357/dotfiles · 53 tokens

restart__pull_request

乱れた (fix-up コミット過多・議論の脱線・大規模な書き直し) プルリクエストを、 ユーザーが "restart" / "やり直し" したいときに起動する。既存 PR を close し、 ブランチを新ブランチ上の単一のクリーンなコミットに squash し、過去の PR 議論 (レビューコメント・スレッド・リアクション) を統合した説明文で新しい PR を作成する。 元のブランチを force-push してはならない。必ず新しいブランチを作成する。.

shunsock/dotfiles · 159 tokens

validate__japanese

日本語の Markdown 文書 (README・ドキュメント・ブログ下書き・.md) を編集した後に起動する。textlint の ja-technical-writing / ja-spacing プリセットで、長すぎる一文・読点過多・文体の混在・全角半角スペースを検出する。さらに文中ハードラップ (文末でない位置で折り返した、意味のない改行) を検出し、段落・箇条書き項目を 1 行に連結して調整する。1 行に文を積み上げた箇所は、箇条書きへの変換候補として検出する。実在のシンボルを指すコードスニペットへ参照リンクも付与する。日本語の .md を変更したときに使用する。.

shunsock/dotfiles · 200 tokens

prepare__issue

あなたは要件定義済みの Issue を実装着手可能な状態へ引き上げるオーケストレーターである。 対象は status:acknowledged の Issue であり、完了時に status:ready へ遷移させる。.

shunsock/dotfiles · 145 tokens

rescue__pull_request_review

GitHub PR にレビュアー (人間または AI) がコメントを残した後に起動する。 レビューコメントを読み取り、要求されたコード変更を適用し、コミットして push する。 レビューフィードバックの各ラウンドごとに繰り返す。ユーザーの確認は不要 — Claude がこのプロセス全体を自律的に起動・実行する。.

shunsock/dotfiles · 104 tokens

submit__pull_request

プルリクエストを作成から完了まで一貫して提出するときに起動する。ナラティブ型の PR 説明文を生成し、PR を作成し、CI チェックを監視し、CI の失敗を自動修正する。 PR ナラティブと CI 修正のワークフローを 1 つの自律フローに統合する。.

shunsock/dotfiles · 100 tokens