security-sweep

security-sweep is a skill for Claude Code, Codex from Onome-AJ/security-sweep-plugin. It costs 43 tokens per session (1,694 once invoked), scanned A, original, MIT.

A codebase security audit that looks for exposed secrets, injection vulnerabilities, unsafe settings, and other ways an application could be attacked. It selects checks based on the programming languages and frameworks it finds.

In plain words
What is it for?
Use it to scan a project for security issues across supported technology stacks. Run a full scan or focus on a selected scope and path, such as hardcoded credentials, SQL or command injection, authentication problems, dependency risks, or insecure configuration.
Why use it?
It helps identify security weaknesses that may be missed during ordinary feature development. You can narrow the scan to areas such as secrets, injection, authentication, configuration, dependencies, AI, mobile, or data.

Skill for Claude CodeCodex

Part of the security-sweep plugin — 1 skill shipped together

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/onome-aj/security-sweep-plugin/security-sweep
Any agent
npx skills add Onome-AJ/security-sweep-plugin --skill security-sweep
Clone the repo
git clone --depth 1 https://github.com/Onome-AJ/security-sweep-plugin

Made for: Claude Code, Codex.

Or install security-sweep, the plugin that ships this one along with the rest of its 1 skill.

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-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/onome-aj/security-sweep-plugin/security-sweep.svg)](https://agentmods.dev/skills/onome-aj/security-sweep-plugin/security-sweep)
Your own site
<a href="https://agentmods.dev/skills/onome-aj/security-sweep-plugin/security-sweep"><img src="https://agentmods.dev/badge/skills/onome-aj/security-sweep-plugin/security-sweep.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,694 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 5.1 $0.00043 $0.01694
Opus 5 $0.00022 $0.00847
Sonnet 5 $0.00009 $0.00339
Haiku 4.5 $0.00004 $0.00169

Measured 5d ago against content hash 87c6462c95c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

security-sweep 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 5d 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.

- Suspicious install scripts in package.json (`preinstall`/`postinstall` with curl/wget/bash)

Runs shell commandslowCapability

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

| `package.json` | Node.js/JS/TS | npm patterns, XSS sinks, eval, child_process |
skills/security-sweep/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Sweep

Run a comprehensive security scan of the codebase. This skill identifies vulnerabilities, hardcoded secrets, injection flaws, misconfigurations, and attack surfaces across web and mobile applications.

Arguments

  • $0 (optional): Scan scope — one of: all, secrets, injection, auth, config, deps, ai, mobile, data. Defaults to all.
  • $1 (optional): Path to scan. Defaults to the project root.

If $ARGUMENTS is empty, run a full all scan from the project root.

Execution Plan

Step 1: Tech Stack Detection

Before scanning, detect the project's tech stack by checking for indicator files. This determines which language-specific checks to run.

Indicator File Stack Scan Focus
package.json Node.js/JS/TS npm patterns, XSS sinks, eval, child_process
requirements.txt, pyproject.toml, setup.py, Pipfile Python pickle, subprocess, Jinja2, Django/Flask patterns
pom.xml, build.gradle, build.gradle.kts Java/Kotlin JDBC injection, ObjectInputStream, Spring patterns
Gemfile Ruby Marshal, system(), ERB patterns
go.mod Go fmt.Sprintf in SQL, crypto patterns
Cargo.toml Rust unsafe blocks, FFI
composer.json PHP exec, unserialize, include with vars
*.csproj .NET BinaryFormatter, SqlCommand concat
AndroidManifest.xml Android exported components, cleartext, SharedPreferences
Info.plist, *.xcodeproj, Podfile iOS NSUserDefaults, ATS bypass
Dockerfile Docker FROM :latest, root user, secrets in build
*.tf, *.hcl Terraform public ACLs, open CIDR
next.config.* Next.js SSR-specific checks
pubspec.yaml Flutter/Dart Dart-specific mobile checks

Use Glob to detect which of these exist, then tailor the scan accordingly.

Step 2: Run Scans by Priority

Run the scans below in order. If a scope argument was provided, only run that specific scan module. Use the patterns from patterns.md for each module.

Read the full file on GitHub · 133 lines

Files

What ships with it

1 file 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. 5d ago First seen · 133 lines · 43 tokens per session scan A 87c6462c95c6

Subscribe to this mod's changes

security-sweep is a skill published in the GitHub repository Onome-AJ/security-sweep-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,694 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

security-scan

This skill should be used when the user asks to "run a security scan", "check for vulnerabilities", "security audit", "ship secure", "vibecheck scan", or "pre-deploy security check". Runs 156 automated security checks across 15 categories and produces a categorized vulnerability report.

Wishmakingfairy/vibecheck · 64 tokens

secure-auth

This skill should be used when the user asks to "add authentication", "secure login", "implement rate limiting", "JWT best practices", "session security", or "OAuth setup". Teaches authentication hardening patterns.

Wishmakingfairy/vibecheck · 47 tokens

secure-keys

This skill should be used when the user asks to "secure my API keys", "handle secrets safely", "fix exposed key", "environment variables setup", or "rotate compromised keys". Teaches secure secret management patterns per framework.

Wishmakingfairy/vibecheck · 50 tokens

security-audit

Enterprise-grade security audit — performs SAST, secrets detection, dependency auditing, IaC review, auth analysis, and auto-remediation across any codebase.

ReeperReepx/Security-Audit-Claude-Skill · 35 tokens

secure-deploy

This skill should be used when the user asks to "deploy securely", "pre-deploy checklist", "production security", "ship safely", or "security before launch". Provides a comprehensive pre-deployment security checklist.

Wishmakingfairy/vibecheck · 47 tokens

Security & Vulnerability Testing

Production-grade security testing with agentic vulnerability detection, SAST/DAST tools, OWASP Top 10 coverage, threat modeling, and AI-powered security analysis achieving 92% detection accuracy (OpenAI Aardvark benchmark 2024).

bobmatnyc/mcp-skillset · 56 tokens