What is zero-day-research-skill?

A research workflow for finding previously unknown vulnerabilities in source code, compiled programs, firmware, custom frameworks, protocols, and internal APIs. It combines code review and binary analysis with tools such as Semgrep, CodeQL, Ghidra, and IDA Pro.

Use it to review source code, inspect binaries and firmware, analyze custom parsers and business logic, and search for new security flaws.

It helps investigate custom software that ordinary scanners may miss because its bugs and behavior are not already known.

zero-day-research-skill — Skill for Claude Code by akashrpatil

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/akashrpatil/awesome-offensive-security-skills

agentmods

npx agentmods add skills/akashrpatil/awesome-offensive-security-skills/zero-day-research-skill

Made for: Claude Code.

Or install cyberskills-elite, the plugin that ships this one along with the rest of its 191 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/zero-day-research-skill/github.svg)](https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/zero-day-research-skill)

Your own site

<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/zero-day-research-skill"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/zero-day-research-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/zero-day-research-skill"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/zero-day-research-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,011 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00048	$0.03011
Opus 5.5	$0.00019	$0.01204
Sonnet 5.5	$0.00010	$0.00602
Haiku 4.5	$0.00005	$0.00301

Measured 2mo ago against content hash 1508264f1e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zero-day-research-skill scanned grade A 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 2mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Command: exec(), system(), child_process

skills/bug-hunting/methodology/zero-day-research-skill/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zero Day Research Skill

When to Use

When standard vulnerability scanning yields no results on a hardened target.
When the target has open-source components or published source code.
When you have access to compiled binaries/firmware that need reverse engineering.
When hunting for vulnerabilities that are NOT in any public database or training data.
When targeting custom frameworks, proprietary protocols, or internal APIs.

Prerequisites

Strong understanding of memory corruption, logic flaws, and authentication patterns
Source code access (GitHub, GitLab, leaked repos) OR binary analysis tools
Static analysis tools: Semgrep, CodeQL, Joern
Binary analysis: Ghidra, IDA Pro, or Radare2
Claude Code CLI for AI-augmented code review

Core Concept

"We built a Zero Day Research skill using Eugene's book methodology — it finds vulnerabilities in source code and binaries that normal training data has never seen." — Episode 166

Why AI + Source Code = Zero Days

AI training data contains known vulnerability patterns. Source code of YOUR target contains unique business logic, custom parsers, and proprietary protocols that no AI has ever analyzed. When you feed that source code to Claude with the right instructions, Claude finds patterns similar to known bugs but in never-before-audited code.

Known Vuln Pattern (training data): SQL injection via string concatenation
Your Target's Code:                 Custom query builder with template literals
Claude's Finding:                   Template literal injection → zero day

Workflow

Phase 1: Source Code Acquisition

Source	How to Obtain	Legal Status
Open-source dependencies	npm, pip, Maven — `package.json` → GitHub	✅ Public
Client-side JavaScript	Browser DevTools → Sources tab → beautify	✅ Public (delivered to you)
Mobile app decompilation	APKTool / jadx (Android), Hopper (iOS)	⚠️ Check program terms
Server-side source maps	`//# sourceMappingURL=` in JS files	✅ If accessible (misconfig = finding)
Git history exposure	`/.git/` directory on web server	✅ If accessible (misconfig = finding)
Binary firmware	Firmware update files from vendor site	⚠️ Check program terms

Read the full file on GitHub · 315 lines

Changes

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.

2mo ago First seen · 315 lines · 48 tokens per session scan A 1508264f1e75

Subscribe to this mod's changes

zero-day-research-skill is a skill published in the GitHub repository akashrpatil/awesome-offensive-security-skills (16 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 3,011 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

0day Research Security binary-analysis methodology reverse-engineering source-code-audit vulnerability-research zero-day

zero-day-research-skill next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zero-day-research-skillakashrpatil/awesome-offensive-security-skills	Skill	16	6mo ago	Apache-2.0	A	48	Claude Code
dataflow-analysisvulhunt-re/skills	Skill	16	8mo ago	none	A	40	Claude Code
call-sitesvulhunt-re/skills	Skill	16	8mo ago	none	A	35	Claude Code
functionsvulhunt-re/skills	Skill	16	8mo ago	none	A	42	Claude Code
byte-pattern-matchingvulhunt-re/skills	Skill	16	8mo ago	none	A	48	Claude Code
code-pattern-matchingvulhunt-re/skills	Skill	16	8mo ago	none	A	41	Claude Code
btp-ba2-clivulhunt-re/skills	Skill	16	8mo ago	none	A	56	Claude Code

zero-day-research-skill