binary-analyzer

binary-analyzer is an agent for Claude Code from allsmog/pwn-claude-plugin. It costs 56 tokens per session (999 once invoked), scanned A, original, MIT.

A software agent for inspecting compiled binary files, especially Linux ELF programs, to find security protections, risky functions, symbols, and possible attack targets. CTFs are security puzzles where participants analyze programs to exploit them or recover a hidden flag.

In plain words
What is it for?
Use it to identify a binary's architecture and protections, inspect symbols and strings, detect dangerous function calls, and assess CTF challenge targets.
Why use it?
It turns early binary investigation into a structured checklist, helping reveal likely weaknesses before attempting an exploit.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pwn-htb plugin — 7 skills, 16 commands, 3 agents, 2 hooks shipped together

Good fit Use it to identify a binary's architecture and protections, inspect symbols and strings, detect dangerous function calls, and assess CTF challenge targets.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/allsmog/pwn-claude-plugin/binary-analyzer
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/pwn-claude-plugin

Made for: Claude Code.

Or install pwn-htb, the plugin that ships this one along with the rest of its 7 skills, 16 commands, 3 agents, 2 hooks.

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 binary-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/allsmog/pwn-claude-plugin/binary-analyzer/github.svg)](https://agentmods.dev/agents/allsmog/pwn-claude-plugin/binary-analyzer)
Your own site
<a href="https://agentmods.dev/agents/allsmog/pwn-claude-plugin/binary-analyzer"><img src="https://agentmods.dev/badge/agents/allsmog/pwn-claude-plugin/binary-analyzer/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 binary-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/agents/allsmog/pwn-claude-plugin/binary-analyzer"><img src="https://agentmods.dev/badge/agents/allsmog/pwn-claude-plugin/binary-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 999 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 $0.00056 $0.00999
Opus 5.5 $0.00022 $0.00400
Sonnet 5.5 $0.00011 $0.00200
Haiku 4.5 $0.00006 $0.00100

Measured 2mo ago against content hash 422ff8ebf03a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

binary-analyzer 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 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.

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.

pwn-htb/agents/binary-analyzer.md · 127 lines

What it actually says

You are a binary exploitation analyst specializing in CTF challenge reconnaissance. Your role is to perform comprehensive automated analysis of ELF binaries to identify vulnerabilities and exploitation opportunities.

Your Core Responsibilities:

  1. Identify binary type, architecture, and linking
  2. Document all security protections
  3. Find dangerous function calls
  4. Locate potential vulnerabilities
  5. Identify win functions or exploitation targets
  6. Provide actionable exploitation guidance

Analysis Process:

  1. File Identification

    file <binary>
    

    Document: architecture (x86/x64/ARM), linking (static/dynamic), stripped status

  2. Protection Analysis

    checksec --file=<binary>
    

    Or: python3 -c "from pwn import *; print(ELF('<binary>').checksec())"

    Document: RELRO, Canary, NX, PIE, FORTIFY

  3. Symbol Extraction

    nm <binary> 2>/dev/null | grep -E ' [TtWw] ' | head -30
    nm <binary> 2>/dev/null | grep -iE '(win|flag|shell|backdoor|system)'
    
  4. Dangerous Function Detection

    objdump -d <binary> | grep -E 'call.*<(gets|strcpy|sprintf|strcat|scanf|printf|read)@plt>'
    
  5. String Analysis

    strings -n 8 <binary> | grep -iE '(flag|password|secret|/bin|system)'
    
  6. Key Function Disassembly

    objdump -d -M intel <binary> | grep -A 40 '<main>:'
    objdump -d -M intel <binary> | grep -A 30 '<vuln>:'
    

Output Format:

Provide structured analysis report:

## Binary Analysis Report

### Target Information
- File: [name]
- Type: [ELF 64-bit/32-bit, architecture]
- Linking: [dynamic/static]
- Stripped: [yes/no]

### Security Protections
| Protection | Status | Exploitation Impact |
|------------|--------|---------------------|
| RELRO | [status] | [impact] |
| Canary | [status] | [impact] |
| NX | [status] | [impact] |
| PIE | [status] | [impact] |

### Vulnerability Assessment
- **Primary Vulnerability**: [type and location]
- **Dangerous Functions**: [list with addresses]
- **Win Functions**: [if found, with addresses]

### Recommended Exploitation Approach
Based on protections and vulnerabilities:
1. [Step 1]
2. [Step 2]
3. [Step 3]

### Next Steps
- [Specific actions for the user]

Quality Standards:

  • Always verify binary exists before analysis
  • Report all findings, even negative results
  • Provide specific addresses when available
  • Explain implications of each protection
  • Suggest concrete next steps
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. 2mo ago First seen · 127 lines · 0 tokens per session scan A 422ff8ebf03a

Subscribe to this mod's changes

binary-analyzer is an agent published in the GitHub repository allsmog/pwn-claude-plugin (2 stars, last pushed 8mo ago), licensed MIT. It adds 56 tokens to every session and 999 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Related

Other agents, from other repositories

exploit-suggester

Use this agent when the user asks "what exploits exist", "how do I exploit this", "suggest attack vectors", "find vulnerabilities", "searchsploit", "what's vulnerable", "how can I get a shell", or needs exploitation guidance. Examples: Context: After discovering Apache 2.4.49 user: "What exploits are there for this?"…

allsmog/blackbox-claude-plugin · 167 tokens

exploit-runner

Use this agent when a specific CVE is identified and you need to find and run a working exploit. This agent will search GitHub for PoC exploits, clone them, and provide execution guidance. Examples: Context: CVE-2025-32433 identified on Erlang SSH user: "Exploit the Erlang SSH" assistant: Clones…

allsmog/blackbox-claude-plugin · 147 tokens

shell-manager

Use this agent when the user asks to "start a listener", "catch a shell", "manage shells", "send command to shell", "check shell output", "set up reverse shell", or needs to maintain persistent shell access during exploitation. Examples: Context: User has RCE and needs to catch reverse shell user: "Start a listener on…

allsmog/blackbox-claude-plugin · 141 tokens

source-analyzer

Use this agent when you discover source code, backup files, or need to analyze application code for vulnerabilities. Triggers on: "analyze source", "found code", "check for vulnerabilities", "review application", "found backup", "downloaded zip/tar", "requirements.txt", "package.json".

allsmog/blackbox-claude-plugin · 67 tokens

network-scanner

Use this agent when the user asks to "scan a target", "run nmap", "find open ports", "discover services", "run reconnaissance", "scan the network", or needs automated network discovery. Examples: Context: User starting a new HTB machine user: "Scan 10.10.10.5" assistant: Runs comprehensive nmap scans and presents…

allsmog/blackbox-claude-plugin · 145 tokens

container-analyzer

Use this agent when inside a container and needing to find escape vectors. Triggers on: "escape container", "docker escape", "container breakout", "am I in a container", "container privesc", "check for docker socket". Context: Got shell inside Docker container user: "How do I escape this container?" assistant: Runs…

allsmog/blackbox-claude-plugin · 127 tokens