claude-red is a library of structured skills that give Claude specialized offensive-security methods for areas such as web vulnerabilities, shellcode, exploit development, and identity systems. It is intended for authorized red-team work, bug-bounty triage, security research, CTF preparation, and operator training. Its catalogue contains the project's skills for loading these security specializations into Claude.
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.
npx skills add SnailSploit/Claude-Red --skill offensive-krack-fragattacksgit clone --depth 1 https://github.com/SnailSploit/Claude-RedWrote 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.
[](https://agentmods.dev/skills/snailsploit/claude-red/offensive-krack-fragattacks)<a href="https://agentmods.dev/skills/snailsploit/claude-red/offensive-krack-fragattacks"><img src="https://agentmods.dev/badge/skills/snailsploit/claude-red/offensive-krack-fragattacks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/snailsploit/claude-red/offensive-krack-fragattacks"><img src="https://agentmods.dev/badge/skills/snailsploit/claude-red/offensive-krack-fragattacks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 84 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Privilege Escalation · line 85 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 33 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 55 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 82 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 88 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00125 | $0.01135 |
| Opus 5.5 | $0.00050 | $0.00454 |
| Sonnet 5.5 | $0.00025 | $0.00227 |
| Haiku 4.5 | $0.00013 | $0.00113 |
Grade B, and why
offensive-krack-fragattacks scanned grade B with 1 finding 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo ./krack-test-client.py --interface wlan0 How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KRACK & FragAttacks
Two attack families against WPA2 client implementations. Both well-disclosed (KRACK 2017, FragAttacks 2021) and largely patched on modern OSes — but the embedded/IoT long tail keeps them in scope for many engagements.
When These Apply
| Family | Target | Patch Status |
|---|---|---|
| KRACK | WPA2 supplicants in 4-way handshake / GTK / FT / TDLS | Major OSes patched 2017–2018 |
| FragAttacks | Frame fragmentation/aggregation across WPA2/3 | Most stacks patched 2021–2022 |
Probability of success today is high only against:
- Embedded OEM devices (cameras, sensors, point-of-sale)
- Old Android phones (<8 unpatched)
- Industrial / SCADA Wi-Fi clients
- Wi-Fi-enabled toys, smart bulbs, no-name IoT
Modern Win11 / iOS 16+ / Android 13+ / hostapd-2.10 are mitigated.
KRACK — Key Reinstallation
The 4-way handshake's M3 retransmission causes the supplicant to reinstall the same PTK with reset nonce/replay counters. Frames encrypted under the reused keystream become decryptable.
# Vanhoef's official test scripts
git clone https://github.com/vanhoefm/krackattacks-scripts
cd krackattacks-scripts/krackattack
sudo ./krack-test-client.py --interface wlan0
# Tests the supplicant on a connected client
Output identifies which CVE variants the client is vulnerable to.
Practical Outcomes
When successful:
- Decryption of WPA2-encrypted frames between client and AP
- TKIP downgrade enables packet injection
- Recovery of session keys for the duration of the affected key cycle
Not a PSK recovery — you don't get the wireless password from KRACK.
FragAttacks — Frame Splicing
FragAttacks abuse 802.11 fragmentation and aggregation to inject frames that mix encrypted and plaintext fragments, or to splice attacker-controlled fragments into legitimate frames.
git clone https://github.com/vanhoefm/fragattacks
cd fragattacks
sudo ./test-fragattacks.py wlan0 --interface wlan0
# Suite of ~12 tests covering each variant
| CVE | Mechanism |
|---|---|
| CVE-2020-24588 | A-MSDU spoofing — inject crafted A-MSDU subframes |
| CVE-2020-24587 | Mixed-key fragment cache poisoning |
| CVE-2020-24586 | Decoupled fragment cache → reuse |
| CVE-2020-26139 | Forwarding plaintext frames before authentication |
| CVE-2020-26140 | Accepting plaintext frames in protected network |
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.
- 1mo ago First seen · 115 lines · 125 tokens per session scan B 12dea4e775fa
offensive-krack-fragattacks is a skill published in the GitHub repository SnailSploit/Claude-Red (9,628 stars, last pushed 15d ago), licensed MIT. It adds 125 tokens to every session and 1,135 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
zhuangxiu-yanshou-zhinan
A Chinese-language knowledge base about checking renovation work. It covers hidden plumbing and electrical work, construction stages, final inspections, and checklists.
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
app-store-opportunity-research
Full-pipeline iOS App Store opportunity research. Discovers underserved niches, analyzes competitor gaps, estimates revenue, produces scored top-3 opportunity reports, and writes MVP PRDs — all through browser and web research. Use when the user wants to find profitable iOS app ideas, research App Store charts…
ghost-writer
Produce first drafts that match a writer's authentic voice using their Voice DNA Document. Consumes DNA documents from writing-dna-discovery skill. Generates 2 meaningfully different drafts with headlines, confidence assessment, decision notes, and DNA refinement suggestions. Collaborative partner that evaluates…
writing-orchestration
This skill should be used when orchestrating complex writing workflows with multiple phases. It provides two-agent orchestration patterns, the two-gate content readiness assessment, 10 baseline writing strategies, 20+ situational strategies, and quality checkpoints. Inspired by the Spiral Writing System.
brainstorm
Collaborative brainstorming partner for multi-session ideation projects. Use when the user wants to brainstorm, ideate, explore ideas, or think through problems—whether for SaaS products, software tools, book ideas, newsletter content, business strategies, or any creative/analytical challenge. Handles session…