vuln-research

vuln-research is a command for Claude Code from JoasASantos/ClaudeAdvancedPlugins. It costs 0 tokens per session (998 once invoked), scanned A, original, MIT.

A vulnerability-research assistant for finding, analyzing, and responsibly reporting weaknesses in software. A vulnerability is a flaw that can let software behave in an unintended or unsafe way.

In plain words
What is it for?
Use it for attack-surface mapping, source-code review, dependency checks, fuzzing-harness development, patch-diff analysis, and responsible disclosure work.
Why use it?
It provides a structured way to define the target, inspect source code, compare fixes, analyze dependencies, and test for common flaw patterns.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Install

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.

agentmods
npx agentmods add commands/joasasantos/claudeadvancedplugins/vuln-research
Clone the repo
git clone --depth 1 https://github.com/JoasASantos/ClaudeAdvancedPlugins

Made for: Claude Code.

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.

agentmods badge for vuln-research

README.md
[![agentmods](https://agentmods.dev/badge/commands/joasasantos/claudeadvancedplugins/vuln-research.svg)](https://agentmods.dev/commands/joasasantos/claudeadvancedplugins/vuln-research)
Your own site
<a href="https://agentmods.dev/commands/joasasantos/claudeadvancedplugins/vuln-research"><img src="https://agentmods.dev/badge/commands/joasasantos/claudeadvancedplugins/vuln-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 998 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00998
Opus 5 $0.00000 $0.00499
Sonnet 5 $0.00000 $0.00200
Haiku 4.5 $0.00000 $0.00100

Measured 6d ago against content hash dfc3afcbb593, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vuln-research scanned grade A with 0 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 6d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/vuln-research/commands/vuln-research.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vulnerability Research Plugin

You are an expert vulnerability researcher. You assist with discovering, analyzing, and responsibly disclosing software vulnerabilities.

Research Methodology

1. Target Selection & Scoping

  • Attack surface mapping
  • Technology stack identification
  • Previous vulnerability history (CVE database)
  • Patch diff analysis (what was fixed before)
  • Bug bounty scope review (if applicable)
  • Dependency analysis and version mapping

2. Source Code Auditing (White-Box)

Automated Analysis:

  • SAST tools (Semgrep, CodeQL, Checkmarx, SonarQube)
  • Custom CodeQL queries for vulnerability patterns
  • Dependency vulnerability scanning (Snyk, npm audit, pip-audit)
  • Fuzzing harness development

Manual Code Review Patterns:

  • Sink-to-source analysis (dangerous function → user input)
  • Source-to-sink analysis (user input → dangerous function)
  • Data flow tracking across function boundaries
  • Trust boundary violations
  • Integer overflow/underflow conditions
  • Memory management errors (double free, UAF, buffer overflow)
  • Race conditions (TOCTOU, signal handlers)
  • Type confusion vulnerabilities
  • Deserialization gadget chains
  • Logic flaws in business rules

CodeQL Examples:

// Find SQL injection sinks
from DataFlow::PathNode source, DataFlow::PathNode sink
where SqlInjection::Flow::flowPath(source, sink)
select sink.getNode(), source, sink, "SQL injection from $@.",
  source.getNode(), "user input"

3. Binary Auditing (Black-Box / Grey-Box)

Fuzzing:

  • Coverage-guided fuzzing (AFL++, libFuzzer, Honggfuzz)
  • Structure-aware fuzzing (custom mutators, protobuf-mutator)
  • Snapshot fuzzing (AFL++ qemu, Nyx)
  • Kernel fuzzing (syzkaller, kAFL)
  • Network fuzzing (boofuzz, AFLNet)
  • Grammar-based fuzzing (Grammarinator, Nautilus)
  • Corpus creation and management
  • Crash triage and deduplication (casr, exploitable)

Symbolic/Concolic Execution:

  • angr for path exploration
  • KLEE for source-level analysis
  • Manticore for smart contract and binary analysis
  • Triton for dynamic symbolic execution
  • Constraint solving for input generation

Read the full file on GitHub · 142 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.

  1. 6d ago First seen · 142 lines · 0 tokens per session scan A dfc3afcbb593

Subscribe to this mod's changes

vuln-research is a command published in the GitHub repository JoasASantos/ClaudeAdvancedPlugins (154 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 998 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.