security-first-2025

security-first-2025 is a skill for Claude Code from JosiahSiegel/claude-plugin-marketplace. It costs 156 tokens per session (3,632 once invoked), scanned B, original, MIT.

A set of secure patterns for writing Bash scripts in 2025, including checks for untrusted input. Bash is a command-line scripting language used to automate computer tasks.

In plain words
What is it for?
Use it when reviewing or writing security-sensitive scripts and when handling URLs, filenames, environment variables, or Windows paths.
Why use it?
It helps prevent unsafe commands, command injection, accidental exposure of shell history, and other scripting mistakes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the bash-master plugin — 10 skills, 4 commands, 1 agent shipped together

Good fit Use it when reviewing or writing security-sensitive scripts and when handling URLs, filenames, environment variables, or Windows paths.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/josiahsiegel/claude-plugin-marketplace/security-first-2025
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 JosiahSiegel/claude-plugin-marketplace --skill security-first-2025
Clone the repo
git clone --depth 1 https://github.com/JosiahSiegel/claude-plugin-marketplace

Made for: Claude Code.

Or install bash-master, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 1 agent.

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 security-first-2025

README.md
[![agentmods](https://agentmods.dev/badge/skills/josiahsiegel/claude-plugin-marketplace/security-first-2025/github.svg)](https://agentmods.dev/skills/josiahsiegel/claude-plugin-marketplace/security-first-2025)
Your own site
<a href="https://agentmods.dev/skills/josiahsiegel/claude-plugin-marketplace/security-first-2025"><img src="https://agentmods.dev/badge/skills/josiahsiegel/claude-plugin-marketplace/security-first-2025/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 security-first-2025

Your own site · 80×15
<a href="https://agentmods.dev/skills/josiahsiegel/claude-plugin-marketplace/security-first-2025"><img src="https://agentmods.dev/badge/skills/josiahsiegel/claude-plugin-marketplace/security-first-2025.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,632 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00156 $0.03632
Opus 5 $0.00078 $0.01816
Sonnet 5 $0.00031 $0.00726
Haiku 4.5 $0.00016 $0.00363

Measured 12d ago against content hash 9da0ff7e1c4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

security-first-2025 scanned grade B with 3 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 12d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

exec sudo -u "$target_user" "$0" "$@"

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

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

trap 'rm -rf "$TEMP_DIR"' EXIT INT TERM

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

Makes network callslowCapability

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

curl https://example.com/data
plugins/bash-master/skills/security-first-2025/SKILL.md · 586 lines

How it starts

The opening of the file, as written. The whole thing — 586 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚨 CRITICAL GUIDELINES

Windows File Path Requirements

MANDATORY: Always Use Backslashes on Windows for File Paths

When using Edit or Write tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/).

Examples:

  • ❌ WRONG: D:/repos/project/file.tsx
  • ✅ CORRECT: D:\repos\project\file.tsx

This applies to:

  • Edit tool file_path parameter
  • Write tool file_path parameter
  • All file operations on Windows systems

Documentation Guidelines

NEVER create new documentation files unless explicitly requested by the user.

  • Priority: Update existing README.md files rather than creating new documentation
  • Repository cleanliness: Keep repository root clean - only README.md unless user requests otherwise
  • Style: Documentation should be concise, direct, and professional - avoid AI-generated tone
  • User preference: Only create additional .md files when user specifically asks for documentation

Security-First Bash Scripting (2025)

Overview

2025 security assessments reveal 60%+ of exploited automation tools lacked adequate input sanitization. This skill provides mandatory security patterns.

Critical Security Patterns

1. Input Validation (Non-Negotiable)

Every input MUST be validated before use:

#!/usr/bin/env bash
set -euo pipefail

# ✅ REQUIRED: Validate all inputs
validate_input() {
    local input="$1"
    local pattern="$2"
    local max_length="${3:-255}"

    # Check empty
    if [[ -z "$input" ]]; then
        echo "Error: Input required" >&2
        return 1
    fi

    # Check pattern
    if [[ ! "$input" =~ $pattern ]]; then
        echo "Error: Invalid format" >&2
        return 1
    fi

    # Check length
    if [[ ${#input} -gt $max_length ]]; then
        echo "Error: Input too long (max $max_length)" >&2
        return 1
    fi

    return 0
}

# Usage
read -r user_input
if validate_input "$user_input" '^[a-zA-Z0-9_-]+$' 50; then
    process "$user_input"
else
    exit 1
fi

Read the full file on GitHub · 586 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. 12d ago First seen · 586 lines · 156 tokens per session scan B 9da0ff7e1c4b

Subscribe to this mod's changes

security-first-2025 is a skill published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (54 stars, last pushed 2mo ago), licensed MIT. It adds 156 tokens to every session and 3,632 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, 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

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

ast-grep

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…

JanDeDobbeleer/oh-my-posh · 80 tokens

platform-detection

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration.…

dotnet/skills · 146 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

omh-rust

This is a Hermes-native rust workflow skill.

rlaope/oh-my-hermes · 69 tokens

axiom-concurrency

Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.

CharlesWiltgen/Axiom · 43 tokens