Skip to content
Back to skills

Ida Re Triage

ASecurity

Use when triaging an authorized binary/driver/firmware/dump/IDB for RE or vuln research.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 17, 2026
researchgo

Works with

  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 17, 2026

npx -y skills add NetVar1337/agent-skill-canon --skill ida-re-triage --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ida Re Triage?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ida Re Triage
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/netvar1337-ida-re-triage/badge)](https://www.skillsdirectory.com/skills/netvar1337-ida-re-triage)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ida-re-triage
description: "Use when triaging an authorized binary/driver/firmware/dump/IDB for RE or vuln research."
version: 1.0.0
license: MIT
metadata:
  package: unleash-skills
  author: NetVar1337/unleash
  category: re
  upstream: C:\Users\Admin\.agents\skills\ida-re-triage\SKILL.md
---

> Bundled with Unleash skills pack. Source: C:\Users\Admin\.agents\skills\ida-re-triage\SKILL.md

# IDA RE Triage

Start static, preserve evidence, and make analysis changes only when requested.

1. Confirm target, architecture, scope, and a working-copy location. Record SHA-256, file size, architecture, load base, and tool version.
2. If no IDB is active, open the working copy in IDA and wait for auto-analysis before using `idassistmcp`. Use the configured `idassistmcp` only after it responds.
3. Read first: binary metadata, segments, imports, exports, entry points, strings, functions, code, and xrefs. State addresses and evidence in findings.
4. For Windows drivers, trace `DriverEntry`, `DriverObject->MajorFunction`, device creation, and IOCTL dispatch. Treat `METHOD_NEITHER`, `FILE_ANY_ACCESS`, unchecked lengths, arbitrary pointer use, and privileged hardware/process operations as leads to verify, not conclusions.
5. Do not call IDA mutating tools (`patch_bytes`, rename, comments, types, variables, data creation, bookmarks) unless the user explicitly asks. Do not execute the target, attach to a live process, or perform write/allocate/free operations on the target unless explicitly requested.
6. Finish with a concise evidence table: finding, address, data flow, confidence, and next static check. Keep copied inputs and IDBs local to the working area.

Files in this skill

  • SKILL.md1.6 KB
  • agents/openai.yaml43 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.