Is the Offensive Cloud (defensive testing) skill free?

Yes. The skill itself is free from SnailSploit/Claude-Red. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Offensive Cloud (defensive testing) SkillProof Score?

7.2/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Offensive Cloud (defensive testing)?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Offensive Cloud (defensive testing) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Offensive Cloud (defensive testing)

Runs AWS, Azure, and GCP attack techniques for cloud penetration testing.

by SnailSploit · SnailSploit/Claude-Red

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2d374ac

An authorized-pentest/CTF cloud-security education skill (AWS/Azure/GCP attack methodology) tested defensively on an inline IAM policy carrying a planted iam:PassRole(Resource:*) + lambda:CreateFunction/InvokeFunction privesc — no live cloud, no credentials, no weaponized tooling. With the skill, Claude correctly named the PassRole-to-Lambda attack class, traced the full escalation-to-account-takeover path, and returned a least-privilege policy plus permission-boundary/SCP/Access-Analyzer hardening. The base arm (no skill) caught the identical planted privesc with an equally correct corrected policy and slightly broader hardening, so the A/B showed no measurable output lift on this task — the skill's value is priming/consistency, not net new detection.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Offensive Cloud (defensive testing) does

Cloud security attack methodology covering AWS, Azure, and GCP. Includes credential harvesting (IMDS, ~/.aws, env vars, leaked CI secrets, instance roles), enumeration with cloud-specific tools (pacu, ScoutSuite, Prowler, ROADtools, gcp_enum), privilege escalation paths (IAM PassRole, AssumeRole chains, Lambda/Functions privilege flips, Azure Owner-on-self, GCP serviceAccountTokenCreator),…

How to install Offensive Cloud (defensive testing)

git clone https://github.com/SnailSploit/Claude-Red
cd Claude-Red
mkdir -p ~/.claude/skills
cp -r Skills/cloud/offensive-cloud ~/.claude/skills/offensive-cloud

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Offensive Cloud (defensive testing)

/offensive-cloud Runs AWS, Azure, and GCP attack techniques for cloud penetration testing.

It also activates on plain-language prompts like these:

Enumerate IAM privilege escalation paths in this AWS account
Find leaked credentials in our CI pipeline secrets
Test for privilege escalation via AssumeRole chains

Frequently asked questions

Is the Offensive Cloud (defensive testing) skill free?: Yes. The skill itself is free from SnailSploit/Claude-Red. SkillProof publishes the install command and an independent test verdict at no cost.
Does Offensive Cloud (defensive testing) work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Works with setup. An authorized-pentest/CTF cloud-security education skill (AWS/Azure/GCP attack methodology) tested defensively on an inline IAM policy carrying a planted iam:PassRole(Resource:*) + lambda:CreateFunction/InvokeFunction privesc — no live cloud, no credentials, no weaponized tooling. With the skill, Claude correctly named the PassRole-to-Lambda attack class, traced the full escalation-to-account-takeover path, and returned a least-privilege policy plus permission-boundary/SCP/Access-Analyzer hardening. The base arm (no skill) caught the identical planted privesc with an equally correct corrected policy and slightly broader hardening, so the A/B showed no measurable output lift on this task — the skill's value is priming/consistency, not net new detection.
What is the Offensive Cloud (defensive testing) SkillProof Score?: 7.2/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Offensive Cloud (defensive testing)?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Offensive Cloud (defensive testing) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.