reverse-engineering-binaries-with-binary-ninja

reverse-engineering-binaries-with-binary-ninja is a skill for Claude Code, Codex from meltedinhex/analyst-ai-pack. It costs 72 tokens per session (697 once invoked), scanned A, original, Apache-2.0.

A guide to examining compiled programs with Binary Ninja, a tool that presents machine code at several levels of readability and supports Python automation.

In plain words
What is it for?
Use it to enumerate functions and strings, inspect different intermediate-code views, add annotations, and generate scripts that extract analysis results.
Why use it?
It makes difficult code easier to follow by moving from assembly-like instructions to readable pseudo-code. Its scripting interface can repeat analysis and export findings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to enumerate functions and strings, inspect different intermediate-code views, add annotations, and generate scripts that extract analysis results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/meltedinhex/analyst-ai-pack/reverse-engineering-binaries-with-binary-ninja
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.

Any agent
npx skills add meltedinhex/analyst-ai-pack --skill reverse-engineering-binaries-with-binary-ninja
Clone the repo
git clone --depth 1 https://github.com/meltedinhex/analyst-ai-pack

Made for: Claude Code, Codex.

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 reverse-engineering-binaries-with-binary-ninja

README.md
[![agentmods](https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/reverse-engineering-binaries-with-binary-ninja.svg)](https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/reverse-engineering-binaries-with-binary-ninja)
Your own site
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/reverse-engineering-binaries-with-binary-ninja"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/reverse-engineering-binaries-with-binary-ninja.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 697 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 $0.00072 $0.00697
Opus 5 $0.00036 $0.00349
Sonnet 5 $0.00014 $0.00139
Haiku 4.5 $0.00007 $0.00070

Measured 4d ago against content hash 4d8d30d0effd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reverse-engineering-binaries-with-binary-ninja 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyst.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/reverse-engineering-binaries-with-binary-ninja/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reverse Engineering Binaries With Binary Ninja

When to Use

  • You want to reverse a binary with Binary Ninja and automate analysis via its Python API (function enumeration, IL traversal, annotation, extraction).
  • You need to leverage MLIL/HLIL for cleaner analysis of obfuscated code.

Do not use the headless API to execute the sample — Binary Ninja performs static analysis. Run in an isolated environment and treat inputs as malicious.

Prerequisites

  • Binary Ninja with the binaryninja Python API available (the script degrades gracefully and generates a script skeleton if the API is not importable).

Safety & Handling

  • Static analysis does not execute the sample; keep inputs isolated.

Workflow

Step 1: Generate an analysis script skeleton

python scripts/analyst.py skeleton --emit functions,strings --out bn_extract.py

Emits a Binary Ninja Python script that opens a view, iterates functions, and exports functions/strings to JSON using the real API (open_view, bv.functions, bv.get_strings).

Step 2: Choose the IL level

Use LLIL for close-to-assembly, MLIL for variable/SSA reasoning, and HLIL for readable pseudo-code; traverse instructions and operands programmatically.

Step 3: Automate annotation

Rename symbols (func.name), add comments (bv.set_comment_at), and create tags for findings.

Step 4: Run and aggregate

Execute the script (headless or in the UI console) and aggregate the JSON output.

Validation

  • The skeleton uses real API calls (binaryninja.open_view, bv.functions).
  • The chosen IL level matches the analysis goal.
  • Exported JSON contains plausible functions/strings.

Pitfalls

  • Headless licensing differences (Commercial vs Personal) affecting open_view availability.
  • Confusing IL levels and operand structures across LLIL/MLIL/HLIL.
  • Long analysis times on large binaries — scope function ranges.

References

Read the full file on GitHub · 90 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 90 lines · 72 tokens per session scan A 4d8d30d0effd

Subscribe to this mod's changes

reverse-engineering-binaries-with-binary-ninja is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 697 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.

pinkpixel-dev/skills-collection-1 · 43 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…

mukul975/Anthropic-Cybersecurity-Skills · 73 tokens

analyzing-malicious-pdf-with-peepdf

A Chinese-language skill for examining suspicious PDF files with peepdf, pdfid, and pdf-parser. It is intended for static malware analysis, which studies a file without running it.

killvxk/cybersecurity-skills-zh · 50 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.

26zl/cybersec-toolkit · 43 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.

plurigrid/asi · 43 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.

marysatasselshaped667/skills-collection-1 · 43 tokens