mrkeyoor.com_
Sat 12 Sept 13:52 UTC
LLM Toolsevaluationupdated 12 Sept 2026

Claude-Red review

Claude-Red is a library of ready-made instruction files that guide Claude through authorized offensive-security work. It gives operators structured methods for 78 topics, so they do not have to rebuild a testing checklist for every engagement.

trackingstars / 7d
Verdict

Our run installed 35 packages in 54 seconds and built in 1 second, but it had no test target to run. Claude-Red is worth trying if you already have authorization controls and want a broad, neatly indexed set of Claude Code playbooks. Treat it as operator guidance, not as a tested security product or a substitute for evidence capture, peer review, and engagement rules.

We ran it

Install✓ · 54s35 packages · 37 MB
Build✓ · 1s
Testsn/ano test script
Known vulns0(pip-audit)
Repo96 files~425 lines of source · 4.7 MB · 4 CI workflows

Answers from our run

Does Claude-Red build from source?

Dependencies installed in 54 seconds (35 packages), and the build succeeded in 1 seconds. We cloned commit 24d7968 into a clean Debian container with 3 CPUs and no project-specific setup.

Does Claude-Red have tests you can run?

Not through a standard command: the project exposes no test script or target that our harness could run.

Does Claude-Red have known vulnerabilities in its dependencies?

pip-audit found none in the dependency tree at the time of our run.

Who should not use Claude-Red?

Beginners seeking a safe, fully supervised security course, because these are operator instructions rather than lessons

What are the alternatives to Claude-Red?

Anthropic Skills, PayloadsAllTheThings, OWASP Web Security Testing Guide. Our run installed 35 packages in 54 seconds and built in 1 second, but it had no test target to run.

Setup5/5Installed in 54 seconds and built in 1 second
Docs4/5Clear quickstart and a detailed 78-skill index
Community4/53,359 stars, 11 open issues, and a recent push
Maturity3/5Broad scope and CI, but no runnable test target

Who it’s for

Authorized red teams that already use Claude in a controlled workflow
Security researchers and bug bounty hunters who want repeatable checklists
Trainers building guided labs for web, wireless, cloud, and identity testing
Claude Code users who prefer selecting individual skills over one giant prompt

Who it’s NOT for

Beginners seeking a safe, fully supervised security course, because these are operator instructions rather than lessons
Defenders who only need remediation or compliance guidance
Teams expecting a scanner, exploit framework, or evidence-management platform
Anyone testing systems without explicit authorization

Setup reality

Our sandbox run installed 35 packages successfully in 54 seconds, using 37 MB on disk, and the build completed in 1 second. There was no tests script or target, so tests were skipped; pip-audit found 0 known vulnerabilities. The README makes basic use look as easy as cloning the repository or copying a SKILL.md file, and our successful install supports that low-friction picture, but the absence of a runnable test suite leaves users without an automated check that all 78 skills remain structurally valid.

It turns security methods into selectable Claude instructions

Claude-Red is not a vulnerability scanner, exploitation framework, or hosted service. It is a collection of 78 structured SKILL.md files that tell Claude how to approach particular offensive-security problems. The index spans 23 categories, including web applications, identity, Active Directory, wireless, cloud, mobile, exploit development, fuzzing, containers, CI/CD, cryptography, post-exploitation, supply chain, social engineering, network attacks, and AI security. The aim is to keep an assistant on a stable procedure instead of letting it jump between ideas or omit checks.

The project packages those 78 procedures as skills that load when a matching topic is discussed. According to the README, mentioning SQL injection can activate the relevant skill, while unused skills do not consume context. Stated use cases include authorized red teams, bug bounty triage, security research, CTF preparation, training, and attack-surface exploration. Because topics include EDR evasion, persistence, and data exfiltration, strict engagement boundaries remain essential.

What happened when we ran it

We cloned commit 24d7968 into an unprivileged Debian container with 3 CPUs, 8 GB of RAM, no secrets, and Python 3.12. The checkout contained 96 files, about 425 lines of source, and occupied 4.7 MB. Installation succeeded in 54 seconds, adding 35 packages and using 37 MB on disk. The build then succeeded in 1 second. Those are practical numbers for evaluating or adding the repository to an isolated workstation without a long provisioning cycle.

Our run found no tests script or target, so the test step was skipped rather than passed. There was also no tests directory and no Dockerfile, while 4 CI workflow files were present. A pip-audit scan reported 0 known vulnerabilities in the installed dependencies. This is encouraging dependency hygiene for the exact environment and commit we measured, but it does not validate the accuracy, safety, or formatting of 78 instruction files. The clearest lab finding is mixed: setup was quick on our box, while automated behavioral coverage was unavailable.

The index is unusually useful for choosing the right playbook

The strongest design choice is the concrete taxonomy. Web testing alone has 16 skills, separating SQL injection, XSS, SSRF, SSTI, XXE, IDOR, file upload, deserialization, race conditions, request smuggling, GraphQL, WAF bypass, and business-logic testing. Wireless is split into 14 skills rather than treated as one generic subject. Operators can install everything, use sparse checkout for selected directories, pipe one file into Claude Code as a system file, or paste one into a Claude.ai project.

The descriptions are specific enough to route work before opening a file. The Active Directory entry names Kerberoasting, ACL abuse, ADCS ESC1-15, delegation, and hybrid identity; the OAuth entry calls out redirect URI abuse, token leakage, and PKCE bypass. That is more useful than a directory of vaguely named prompts. The MIT license keeps reuse straightforward, and the install script accepts an explicit target or category selector.

The main weakness is trust, not installation

The project asks users to place powerful third-party instructions into an assistant's operating context. Yet our snapshot exposed no runnable test target for checking file structure, metadata, routing collisions, or unintended changes across 78 skills. Four CI workflow files show that automation exists, but the supplied evidence does not establish what those workflows verify. The repository also does not replace authorization, tool installation, credential isolation, command review, evidence storage, or a final human-written report.

Some README claims should be treated as promises to inspect, not results we independently proved. Our 1-second build says the repository builds in the measured container; it does not show that conversational triggers always load the best skill or that advice handles every edge case. Before operational use, teams should review the exact files they plan to load, pin a commit, restrict permissions, and record which guidance influenced each finding.

Activity looks healthy, although release cadence is still unclear

The repository had 3,359 stars and 11 open issues in the supplied snapshot. Its latest release was v0.3.0 on August 30, 2026, and the last push occurred one second before the release timestamp, only 13 days before our September 12 run. Taken together, adoption and recency look healthy rather than abandoned. However, one release date cannot establish a regular cadence, and the open-issue count alone does not reveal response time, resolution quality, or maintainer capacity. Community interest is evident; long-term maintenance consistency is less certain.

It belongs beside an engagement process, not above it

In a real stack, Claude-Red fits between an authorized operator's question and the tools they already control. Use one reviewed SKILL.md to structure testing, then run approved tools separately, capture raw evidence, and verify every conclusion before reporting it. For web-only work, OWASP's testing guide offers a neutral shared standard; PayloadsAllTheThings is better for direct technique references. Anthropic's broader skills repository fits when security is only 1 part of the workflow.

The practical recommendation is narrow: try v0.3.0 in an isolated profile if Claude Code is already part of an authorized security program and the 78-topic index saves preparation time. Do not give the collection unattended production access or confuse structured instructions with validated findings. The low setup cost makes a pilot easy, while the missing test target calls for local review and change control. Claude-Red is a useful playbook shelf, not an autonomous red team.

Alternatives

ProjectWhat it isPick it when
Anthropic Skills gh↗A broader official collection and specification examples for reusable Claude skills.Pick this instead when you want general-purpose skill patterns or a vendor-maintained starting point, not an offensive-security library.
PayloadsAllTheThings gh↗A large reference of payloads and techniques organized by vulnerability class.Pick this instead when you need concrete manual-testing references and payload examples without tying the workflow to Claude.
OWASP Web Security Testing GuideA community-maintained methodology for planning and conducting web application security tests.Pick this instead when auditability, shared terminology, and a platform-neutral web-testing standard matter more than AI-guided breadth.

What people are saying

  1. [github-trending] SnailSploit/Claude-Red

Sources

  1. Claude-Red GitHub repository

More llm tools reviews

knowledge-work-plugins · llamafile · OpenContext · hyperresearch · prompt-optimizer · agent-router · the whole board →