agentleFS
zyphr-labszyphr-labs/bounty-harness/.claude/skills/binary-analysis/SKILL.md

binary-analysis

Skill1 starsChanged 3 months agoMITView on GitHub

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We found no rules to list in this file: it reads as prose or reference rather than instructions.

Files
SKILL.md

Binary Analysis

Overview

Static and dynamic analysis of Windows binaries shipped by bounty targets: desktop apps, updaters, agents, packed downloadables. Static triage is stdlib-only and runs anywhere; dynamic sessions drive a local x64dbg debugger through its MCP plugin (duty1g/x64dbg-mcp-server, 71 tools over HTTP with bearer auth). All analysis is LOCAL on files you legitimately possess - this skill never interacts with remote target infrastructure.

Quick Reference

  • Skill: binary-analysis
  • Version: 1.0.0
  • Bounded Context: BinaryAnalysisContext
  • Required tools: python3 (static); x64dbg + x64dbg-mcp-server plugin (dynamic)
  • Risk tier: passive (toward targets - local file analysis only)

Workflow Selection

IntentWorkflowTier
First-pass on one executablepe-triagepassive
Triage a folder of downloadspe-triage-batchpassive
List tools on live x64dbg sessionmcp-toolspassive
Read registers/modules/strings, set breakpointsmcp-callpassive

Setup (one-time)

  1. Download x64dbg from https://x64dbg.com
  2. Install the MCP plugin per https://github.com/duty1g/x64dbg-mcp-server (copy dist/ into the x64dbg root; server auto-starts on ports 9094/9095)
  3. Copy the auto-generated bearer token: echo TOKEN > .bb/x64dbg.token

Bounty-Relevant Uses

  • Desktop app programs: analyze deeplink/protocol handlers, update mechanisms, license checks before touching them dynamically
  • Packed binaries: triage flags UPX/VMP/Themida-style sections; dump after OEP via mcp-call pe-analysis intent, then re-triage the unpacked image
  • Crash triage: breakpoint at watched APIs while reproducing to prove control
  • Config discovery: strings/pattern intents reveal embedded endpoints feeding back into recon scope

Evidence Required

  • Static: full triage.json with section table and import watchlist hits
  • Dynamic: mcp_call.json snapshots timestamped against your manual interaction steps; never include license keys or user data found in memory beyond what proves the finding

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.