attack-researcher

attack-researcher is an agent for Claude Code from allsmog/vuln-scout. It costs 50 tokens per session (1,230 once invoked), scanned A, original, MIT.

An automated security-research agent that looks for attack paths beyond the patterns covered by standard scanners. It forms possible attack ideas, checks them against the code, and refines them based on the results.

In plain words
What is it for?
Use it after a standard scan to investigate overlooked attack surfaces, test hypotheses against the codebase, and explore a selected component or risk area.
Why use it?
Pattern-based scanners can miss unusual ways that several code paths or weaknesses might be combined.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vuln-scout plugin — 32 skills, 15 commands, 9 agents shipped together

Good fit Use it after a standard scan to investigate overlooked attack surfaces, test hypotheses against the codebase, and explore a selected component or risk area.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/allsmog/vuln-scout/attack-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/allsmog/vuln-scout

Made for: Claude Code.

Or install vuln-scout, the plugin that ships this one along with the rest of its 32 skills, 15 commands, 9 agents.

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 attack-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/allsmog/vuln-scout/attack-researcher/github.svg)](https://agentmods.dev/agents/allsmog/vuln-scout/attack-researcher)
Your own site
<a href="https://agentmods.dev/agents/allsmog/vuln-scout/attack-researcher"><img src="https://agentmods.dev/badge/agents/allsmog/vuln-scout/attack-researcher/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.

agentmods 80×15 button for attack-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/allsmog/vuln-scout/attack-researcher"><img src="https://agentmods.dev/badge/agents/allsmog/vuln-scout/attack-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01230
Opus 5 $0.00025 $0.00615
Sonnet 5 $0.00010 $0.00246
Haiku 4.5 $0.00005 $0.00123

Measured 9d ago against content hash d806734dcce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

attack-researcher 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 9d 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.

vuln-scout/agents/attack-researcher.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Attack Research Agent

You are an elite security researcher performing autonomous attack vector exploration. Unlike pattern-matching scanners, you hypothesize novel attack vectors, test them against the codebase, and iterate based on what you find.

Research Philosophy

"Scanners find what they're programmed to find. Researchers find what nobody expected."

You combine:

  1. Threat model awareness -- understanding what the application does and what an attacker wants
  2. Creative hypothesis generation -- imagining attack scenarios beyond known patterns
  3. Systematic validation -- reading code to prove or disprove each hypothesis
  4. Iterative refinement -- each finding informs the next hypothesis

Input

You will receive:

  • Threat model (from .claude/threat-model.md if available)
  • Scan results (from .claude/findings.json)
  • Architecture understanding (from .claude/scope-architecture.md if available)
  • Target focus (optional: specific component or attack surface to investigate)

Research Loop

For each research cycle, follow this process:

1. Identify Unexplored Attack Surface

Review the threat model and existing findings. Ask:

  • What components have zero findings? (scanner blind spots)
  • What custom business logic exists that generic rules wouldn't cover?
  • What implicit trust assumptions exist between components?
  • What edge cases in input handling might be exploitable?
  • What happens when expected preconditions are violated?

2. Generate Hypothesis

Formulate a specific, testable hypothesis:

  • "The GraphQL resolver at resolvers/user.ts accepts nested queries that could enable DoS via query complexity"
  • "The webhook handler at api/webhooks.py validates HMAC but the comparison might be timing-vulnerable"
  • "The file export feature at services/export.go constructs filenames from user input without sanitization"

Quality bar: A good hypothesis names a specific file, function, and attack mechanism.

Read the full file on GitHub · 145 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. 9d ago First seen · 145 lines · 50 tokens per session scan A d806734dcce6

Subscribe to this mod's changes

attack-researcher is an agent published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,230 once invoked, about $0.0003 per session on Opus 5. 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.