analyze-binary

A command for examining suspicious program files with remote security-analysis tools. It uploads a file, performs a quick file check, and supports deeper analysis and decompilation.

In plain words
What is it for?
Use it to upload and inspect suspicious Windows, Linux, or macOS binaries, then carry out sandbox analysis or decompilation.
Why use it?
It helps investigate a potentially harmful file without relying on the coding agent’s local file access. The analysis can reveal what the file is and how it may work.

Command

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/deepbitstechnology/claude-plugins/analyze-binary
Clone the repo
git clone --depth 1 https://github.com/DeepBitsTechnology/claude-plugins
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,085 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00020 $0.01085
Opus 5 $0.00010 $0.00543
Sonnet 5 $0.00004 $0.00217
Haiku 4.5 $0.00002 $0.00109

Measured yesterday against content hash 5c5248bc8b0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-binary 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Call `prepare_upload(file_name="<name to store as>")`. It returns a one-time `curl` command (valid 10 minutes) with an `<ABSOLUTE_LOCAL_PATH>` placeholder.
drbinary-chat-plugin/commands/analyze-binary.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Binary File Analysis

Analyze a suspicious binary file using the remote Dr. Binary MCP server (Rizin triage, sandboxed deep analysis, and Ghidra decompilation).

Usage

Provide the full path to the suspicious file you want to analyze.

Analysis Process

Step 1: Upload the file to the remote workspace

The remote server cannot read your local filesystem, so the file must be uploaded first:

  1. Call prepare_upload(file_name="<name to store as>"). It returns a one-time curl command (valid 10 minutes) with an <ABSOLUTE_LOCAL_PATH> placeholder.
  2. Run that curl yourself with the Bash tool, substituting <ABSOLUTE_LOCAL_PATH> with the absolute path to the local file. The bytes upload directly to the server and never pass through the model context.
  3. After a successful upload, refer to the file by its stored filename (the sandbox CWD is the workspace root) in all subsequent tool calls.

If the link has expired or was already used, call prepare_upload again for a fresh one.

Step 2: Triage with inspect_binary

Call inspect_binary(filepath="<filename>") for fast rz-bin triage:

  1. Basic File Information — file size and type, PE/ELF/Mach-O header, entrypoints
  2. Imports / Exports — API calls and exported functions
  3. Sections — .text, .data, .rsrc, etc.
  4. Strings & Symbols — readable strings and symbol-derived functions

(For hashes like MD5/SHA256, compute them in run_sandbox, e.g. sha256sum <filename>.)

Step 3: Deep analysis with run_sandbox + Rizin

Use run_sandbox(command="rizin -qc '<commands>' <filename>") for focused analysis:

  • aaa; afl — analyze and list functions
  • aaa; pdf @ <func> — decompile/disassemble a specific function
  • izz — strings across the whole file; ii — imports; iE — exports

The sandbox also provides radare2, binwalk, xxd, angr/pwntools/qiling (python3), qemu (qemu-{arch} -strace ...), apktool, jadx, and more. run_sandbox accepts an optional timeout (default 120s, max 600s).

Read the full file on GitHub · 133 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. yesterday First seen · 133 lines · 20 tokens per session scan A 5c5248bc8b0c

Subscribe to this mod's changes

analyze-binary is a command published in the GitHub repository DeepBitsTechnology/claude-plugins (46 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,085 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.