Skip to content
Get packs

Cloud Penetration Testing

Guides an agent through authorized penetration tests of AWS, Azure and GCP accounts, from scoping to reporting.

Source Download skill
Repository
mukul975/Anthropic-Cybersecurity-Skills
Stars
35,430
Licence
Apache-2.0
Files
3 files

What it does

Once installed, the agent follows a structured methodology for testing the security of cloud accounts the user is authorized to assess. It helps define scope under the shared responsibility model, suggests cloud security tools such as ScoutSuite, Prowler, CloudFox and Pacu, walks through checks for IAM privilege escalation, server-side request forgery to cloud metadata services, and lateral movement, and frames findings against the MITRE ATT&CK Cloud matrix. The skill is a methodology with example commands, so the agent can write and suggest commands for the user to review and run.

Great for

  • Security engineers performing authorized cloud penetration tests with a signed scope document
  • Security teams preparing for compliance-mandated annual cloud assessments
  • Students or lab operators practicing cloud attack techniques in isolated test accounts

Skip it if

  • Testing cloud accounts without written authorization, which is illegal and violates provider policies; the skill itself says not to use it that way
  • Testing cloud provider infrastructure or running DDoS simulations, which the skill explicitly excludes
  • Non-security users, since the commands can steal credentials or escalate privileges if pointed at the wrong account

Try asking

  • “Help me write a rules-of-engagement and scope document for a penetration test of our AWS production account.”
  • “Walk me through checking our AWS IAM roles for privilege escalation paths using Pacu and CloudFox.”
  • “Explain how to test our web app for SSRF to the instance metadata service and what the fix looks like.”
  • “Map the findings from our cloud assessment to MITRE ATT&CK Cloud techniques for the report.”
Step-by-step guide: how to use Cloud Penetration TestingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the Apache-2.0 licence and an attribution note.

    conducting-cloud-penetration-testing.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip conducting-cloud-penetration-testing.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip conducting-cloud-penetration-testing.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Only run against accounts you have written authorization to test, and keep the signed scope document with the work.
  • Review every command before execution; prefer an isolated test account over production, and check the included script's logic before running it since its excerpt is truncated.
  • Ask the agent to produce findings mapped to severity, evidence and remediation so the output is usable in a client report.

What's inside

  • references/api-reference.md
  • scripts/agent.py
  • SKILL.md

Redistributed unmodified from mukul975/Anthropic-Cybersecurity-Skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.