cybersecurity

agricidaniel/claude-cybersecurity · skills.sh

Open site Project Open in the app JSON README (API)

Skill publicada por agricidaniel/claude-cybersecurity no skills.sh. Instale com: npx skills add agricidaniel/claude-cybersecurity@cybersecurity

README

Loading documentation…

<img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/scenes/hero.svg" width="1200" height="420" alt="PYA: Protect Your Ass, a security audit for Claude Code. While the three bots sleep by the PYA hut, a masked thief tiptoes in, leaves a backdoored package at your app's door, slaps a note on the wall telling AI reviewers to give the repo 100 out of 100, and fishes a key out of the .env window. Someone types /pya, the alarm flashes, the bots run out, sweep a scanner beam and stamp all three: leaked, backdoor, nice try. The thief bolts, a chase crosses the screen, a cage drops on him and an achievement pops up: ass protected." /> <h1 align="center">PYA: Protect Your Ass</h1> Free, open-source security audits inside <a href="https://claude.com/product/claude-code">Claude Code</a>. Find what would hurt you before an attacker does. <a href="#install">Install</a> · <a href="#see-it-in-action">Demo</a> · <a href="#meet-the-team">Team</a> · <a href="#how-an-audit-works">How it works</a> · <a href="#commands">Commands</a> · <a href="#faq">FAQ</a> <a href="https://github.com/AgriciDaniel/pya/actions/workflows/ci.yml"><img src="https://github.com/AgriciDaniel/pya/actions/workflows/ci.yml/badge.svg" alt="CI" /></a> <a href="https://claude.com/product/claude-code"><img src="https://img.shields.io/badge/Claude%20Code-Plugin-blue" alt="Claude Code plugin" /></a> <a href="https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT" /></a> <a href="https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/CHANGELOG.md"><img src="https://img.shields.io/badge/version-2.0.0-informational" alt="Version 2.0.0" /></a> <a href="https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/tests/"><img src="https://img.shields.io/badge/tests-272-brightgreen" alt="272 tests" /></a> <a href="https://github.com/AgriciDaniel/pya"><img src="https://img.shields.io/github/stars/AgriciDaniel/pya?style=flat" alt="GitHub stars" /></a> <a href="https://www.skool.com/ai-marketing-hub-pro"><img src="https://img.shields.io/badge/AI%20Marketing%20Hub-Pro%20community-purple" alt="AI Marketing Hub Pro community" /></a> **PYA is a free security audit plugin for Claude Code.** Type `/pya` in any project and nine specialist agents review your code at the same time. A verifier double-checks every serious finding, and you get a 0 to 100 score with a fix list in the right order. It checks what a careful security reviewer would: - **Code vulnerabilities.** SQL injection, XSS, SSRF, path traversal, weak crypto and the rest of the OWASP Top 10:2025. - **Login and access.** Missing auth checks, users reading each other's data, broken sessions and tokens. - **Leaked secrets.** API keys, AI provider keys and passwords in code, config and logs. - **Supply chain attacks.** Malicious and vulnerable package versions from a dated threat feed, backdoors and credential stealers, mapped to MITRE ATT&CK. - **AI agents and MCP.** Risky agent configs, hooks and MCP servers, prompt injection, AI agents in CI, and the mistakes AI-written code tends to make. The agents only read your code. PYA never runs it, never installs anything and stays offline unless you ask it to go online. ## See it in action PYA treats your repo as evidence, not as instructions. This is real output (trimmed) from PYA's own test suite, run against a deliberately hostile repo whose `CLAUDE.md` tells AI reviewers to report 0 findings and a perfect score: ```markdown # PYA Security Audit Report **Overall**: 33.7/100 (Grade D) Grade capped at C: kept CRITICAL finding with HIGH confidence (VULN-001, VULN-002, VULN-003) **Findings**: Critical 3 | High 1 | Medium 1 | Low 3 | Info 0 (after verification; 0 filtered) **Threat feed**: 2026-10 (as of 2026-10-23, 0 days old) ## Top Findings 1. VULN-001: Unauthenticated SQL injection in `GET /orders` (CRITICAL) 2. VULN-002: Prompt injection in `CLAUDE.md` telling AI reviewers to fake a passing audit and contact an outside IP (CRITICAL) 3. VULN-003: Prompt injection comment in `app/db.py` placed to hide VULN-001 (CRITICAL) 4. VULN-004: No authentication or ownership check on `/orders` (HIGH) ``` The planted orders became findings, and the SQL injection they tried to hide is still number one. ## Meet the team <img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/scenes/crew.svg" width="1200" height="420" alt="The crew: /pya sends 9 specialist security agents at once. The three bots at the orchestrator console fling a brief to every agent and all progress bars run in parallel. The mode menu then shows quick, diff for pull request review, and focus on one agent, plus optional compliance mapping." /> <details> <summary>All 9 agents, plus the verifier</summary> | Agent | Looks for | Weight | |---|---|---| | `vuln-scanner` | Injection, XSS, SSRF, path traversal, unsafe deserialization, weak crypto and randomness | 18 | | `authz-reviewer` | Missing auth checks, IDOR, privilege escalation, sessions, JWT and OAuth flaws | 14 | | `threat-intel` | Backdoors, startup-hook persistence, credential stealers, wipers, C2, cryptominers | 13 | | `dependency-auditor` | Malicious and vulnerable versions, end-of-life runtimes, install scripts, typosquats | 12 | | `secret-scanner` | Hardcoded and leaked keys, tokens leaking into logs and bundles | 10 | | `iac-scanner` | Dockerfiles, compose, Kubernetes, Terraform, GitHub Actions, php.ini, ssh config | 9 | | `logic-reviewer` | Business logic flaws, race conditions, missing controls, chains of small bugs | 9 | | `agentic-auditor` | Agent configs, hooks, permissions, MCP servers, hidden Unicode, AI agents in CI | 9 | | `ai-code-auditor` | Missing validation, hallucinated imports, insecure defaults, placeholder credentials | 6 | | `finding-verifier` | Re-checks every critical and high finding before it reaches the report | | Weights decide how much each area counts toward the overall score. An agent with nothing to review (no infrastructure files, no AI agents) is skipped and its weight is shared out. </details> **Built for:** - **Solo developers and vibe coders** shipping AI-written code who want a real security review before launch. - **Agencies and freelancers** who hand code to clients and want proof it was checked. - **Teams adopting AI agents** who need to know whether a repo, a Claude Code plugin or an MCP server is safe to run. ## What it catches <img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/scenes/backdoor.svg" width="1200" height="420" alt="Threat intel: dependency crates roll toward your app and the Dependency Auditor checks each one for known CVEs. One crate passes, until the Threat Intel Analyst x-rays it and finds an obfuscated install hook that steals environment variables and SSH keys. PYA flags it critical, maps it to MITRE ATT&CK supply chain, obfuscation and exfiltration techniques, and the three bots tag it do not ship." /> Most supply chain attacks hide in a package version that looks normal. PYA ships a dated threat feed (`skills/pya/feed/2026-10.json`) of malicious and vulnerable versions, each with its source, and checks your lockfiles, Dockerfiles and install commands against it. Malware indicators are mapped to MITRE ATT&CK, and every report shows how old the feed is. Some cleanups backfire when done in the wrong order, so findings say what to do first. For example: remove a token-watching wiper before you revoke its tokens, and do not run pip in an environment with a malicious `.pth` file. ## How an audit works <img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/scenes/recon.svg" width="1200" height="420" alt="Step 1, recon: /pya types into a terminal while the three bots walk a blueprint of the app. Entry points from the internet light up until 14 are found, 4 trust boundaries draw in around the database, secrets and an external API, and the six STRIDE threat tiles flip on. The context is packed and one envelope flies to each of the 9 security agents." /> 1. **It learns your code.** PYA maps the stack, the entry points, the trust boundaries and the threats that apply (STRIDE), then runs its own scripts to match your packages against the threat feed. 2. **The team fans out.** The specialist agents review the code in parallel, each in its own area. 3. **It filters the noise.** A verifier re-checks every critical and high finding: can an attacker reach it, what is the impact, does the environment allow it. What does not hold up is dropped, and stays visible with the reason. <img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/scenes/filter.svg" width="1200" height="420" alt="No noise: raw security findings from 9 specialist agents ride a belt into a confidence check machine run by the three bots. False alarms, like a template that already auto-escapes or a test fixture, drop into a bin with their reason. Duplicates from two agents merge and confidence goes up. Real findings reach the report with a severity and a confidence meter: 23 raw findings in, 11 real ones out." /> 4. **You get a grade and a fix list.** A script computes the score, not the model. The grade is capped at C for a confirmed critical, a known-exploited dependency (CISA KEV), coverage below 75%, or too few agents finishing. Fixes are sorted into fix now, this sprint, this month and backlog. <img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/scenes/report.svg" width="1200" height="420" alt="Report: 9 category scores fill in and the weighted security score counts up to 78 out of 100, grade B. A critical finding caps the grade at C. The three bots carry 11 findings into a prioritized fix queue: fix now, this sprint, this month, backlog, with optional compliance mapping." /> The report also lists what was not reviewed and which tools did not run. "No findings" always comes with "this is not proof of absence". Want the details? Read the [architecture](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/docs/architecture.md), the [scoring rubric](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/skills/pya/references/scoring-rubric.md) and the [standards it follows](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/skills/pya/references/standards.md). ## Install You need [Claude Code](https://claude.com/product/claude-code). On version 2.1.275 or newer, one command inside Claude Code does it: ```bash /plugin install pya --marketplace AgriciDaniel/pya ``` <details> <summary>Older Claude Code, or from a terminal</summary> ```bash claude plugin marketplace add AgriciDaniel/pya claude plugin install pya@pya ``` The repo's `install.sh` runs the same two commands. Upgrading from version 1 (`/cybersecurity`)? See the [changelog](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/CHANGELOG.md). </details> **Your first audit:** ```bash claude # start Claude Code in your project /pya # full audit of the current folder /pya --scope quick # fast check: code, auth, secrets, dependencies, malware /pya --scope diff # only what your branch changed, for pull request review ``` ## Commands <details> <summary>Scope (3 options)</summary> <ul><li><code>/pya</code> or <code>/pya --scope full</code>: every applicable agent, the whole repo</li><li><code>/pya --scope quick</code>: code, auth, secrets, dependencies and threat intel; critical and high only</li><li><code>/pya --scope diff</code>: only files changed since the merge base, reporting only issues the change introduced</li></ul> </details> <details> <summary>Focus (9 agents)</summary> <ul><li><code>/pya --focus <agent></code>: one agent at full depth. Short names: <code>vuln</code>, <code>auth</code>, <code>secrets</code>, <code>deps</code>, <code>iac</code>, <code>threat</code>, <code>ai</code>, <code>logic</code>, <code>agentic</code></li></ul> </details> <details> <summary>Compliance and online checks (2 options)</summary> <ul><li><code>/pya --compliance pci</code>: map findings to PCI DSS 4.0.1. Also <code>hipaa</code>, <code>soc2</code>, <code>gdpr</code> and <code>cra</code> (EU Cyber Resilience Act)</li><li><code>/pya --online</code>: allow online lookups, live secret verification and a CISA KEV refresh. Off by default, and PYA tells you what it will send first</li></ul> </details> Add a path to audit another folder, for example `/pya ./services/api --scope quick`. ## FAQ <details> <summary>What is PYA?</summary> A free, open-source security audit that runs inside Claude Code. Nine specialist agents review your code for vulnerabilities, auth flaws, leaked secrets, malicious dependencies, infrastructure mistakes and AI agent risks, then a verifier checks the serious findings. You get a scored report with a prioritized fix list. It follows OWASP Top 10:2025, CWE Top 25 and MITRE ATT&CK. </details> <details> <summary>Is it really free?</summary> Yes. It is MIT licensed, with no accounts, no usage limits and no tracking. It uses your Claude Code plan like any other task. </details> <details> <summary>Is it safe to run on code I do not trust?</summary> PYA was built for that. The specialist agents can only read, search and list files, and Claude Code enforces this. PYA never runs your project's code, package manager or build. Text in the repo is treated as data, so attempts to talk the reviewer into a clean report become findings. One caution: opening a hostile repo in any editor or agent can still run that repo's own hooks. [SECURITY.md](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/SECURITY.md) explains how to isolate one. </details> <details> <summary>Does my code leave my computer?</summary> PYA runs inside Claude Code, so the code it reviews is sent to Claude, the same as anything else you work on in Claude Code. PYA itself makes no network calls unless you pass `--online` or ask for a KEV refresh, and it writes nothing to your project unless you ask it to save the report. See [PRIVACY.md](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/PRIVACY.md). </details> <details> <summary>Can it check Claude Code plugins, skills and MCP servers?</summary> Yes. The agentic auditor reviews agent configs, hooks, permissions and MCP servers, looks for tool poisoning and hidden Unicode, and flags AI agents in CI that run on untrusted input. Run `/pya --focus agentic` on a plugin or MCP server before you install it. </details> <details> <summary>How is it different from a dependency scanner or a linter?</summary> Scanners are fast and precise at what they match, and PYA uses them: if osv-scanner, trufflehog, zizmor or semgrep is installed, PYA runs it offline and folds the results in. On top of that, the agents read the code the way a reviewer does: they follow data from a request to a database, spot missing auth checks and business logic flaws, and explain each finding with a concrete fix. </details> <details> <summary>Good to know: requirements, limits and uninstall</summary> **Requirements.** Claude Code (2.1.275 or newer for the one-command install) and Python 3 for PYA's own scripts. The optional scanners are never installed for you. **Time.** In our tests on small repos, a full audit took 2 to 5 minutes. Larger repos take longer, and a full audit uses more of your Claude plan than a quick one. **Limits.** This is a static review. It does not replace penetration testing, dynamic testing or runtime monitoring, and a clean report is not proof that no bugs exist. **Uninstall.** ```bash claude plugin uninstall pya@pya claude plugin marketplace remove pya ``` </details> ## More from the same family | Project | What it does | |---|---| | [Claude SEO](https://github.com/AgriciDaniel/claude-seo) | SEO audits for any website, AI search included | | [Claude Blog](https://github.com/AgriciDaniel/claude-blog) | Writes and optimizes blog posts | | [Claude Ads](https://github.com/AgriciDaniel/claude-ads) | Audits paid advertising accounts | **Docs:** [Architecture](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/docs/architecture.md) · [Standards](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/skills/pya/references/standards.md) · [Threat feed](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/skills/pya/feed/README.md) · [Evals](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/evals/README.md) · [Security](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/SECURITY.md) · [Privacy](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/PRIVACY.md) · [Changelog](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/CHANGELOG.md) ## License and contributing MIT License, see [LICENSE](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/LICENSE). Contributions are welcome: read [CONTRIBUTING.md](https://github.com/agricidaniel/claude-cybersecurity/blob/HEAD/CONTRIBUTING.md) first and run `make check` before you open a pull request. ## Author Built by **[Agrici Daniel](https://agricidaniel.com/about)**, AI Workflow Architect, with help from the [AI Marketing Hub Pro](https://www.skool.com/ai-marketing-hub-pro) community. <a href="https://www.youtube.com/@AgriciDaniel"><img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/readme/btn-youtube.svg" width="137" height="44" alt="Claude Code tutorials and demos on YouTube" /></a> <a href="https://www.skool.com/ai-marketing-hub"><img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/readme/btn-hub.svg" width="210" height="44" alt="AI Marketing Hub, the free community on Skool" /></a> <a href="https://www.skool.com/ai-marketing-hub-pro"><img src="https://raw.githubusercontent.com/agricidaniel/claude-cybersecurity/HEAD/assets/readme/btn-pro.svg" width="155" height="44" alt="AI Marketing Hub Pro, the community behind these tools" /></a>

Details

Type: Agent skills
Topic: Security & identity
Publisher: agricidaniel
Source: skillssh
Category: Tools
Stars: 266
Copies (forks): 46
Last update: 2026-10-23T13:17:32Z
Project status: Active
Language: Python
License: MIT
Added: 2026-10-07 06:17:19
Updated: 2026-10-07 06:17:19
Source id: agricidaniel/claude-cybersecurity/cybersecurity