agentleFS
Sign inStart free
MasriyanMasriyan/gemini-security-skills/skills/malware-reverse-engineering/SKILL.md

malware-reverse-engineering

Skill4 starsChanged 5 months agoMITView on GitHub

Malware reverse engineering and suspicious artifact analysis skill for defensive triage, static analysis, dynamic analysis planning, unpacking strategy, indicators of compromise, behavior summaries, YARA/Sigma ideas, and remediation guidance. Use for suspicious binaries, scripts, documents, logs, memory artifacts, sandbox reports, and malware family analysis in isolated environments.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat samples as hostile. Use isolated labs, snapshots, no shared clipboard, no mounted personal directories, and controlled networking.

    line 10
  2. Distinctive:

    Do not provide malware improvement, persistence, stealth, evasion, credential theft, or deployment guidance.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Malware Reverse Engineering

Safety Boundary

  • Treat samples as hostile. Use isolated labs, snapshots, no shared clipboard, no mounted personal directories, and controlled networking.
  • Do not provide malware improvement, persistence, stealth, evasion, credential theft, or deployment guidance.
  • Focus on behavior, indicators, detection, containment, and eradication.

Workflow

  1. Record sample metadata: filename, hashes, size, type, source, timestamp, and handling notes.
  2. Perform static triage: strings, imports, sections, packer hints, scripts/macros, config blobs, and suspicious capabilities.
  3. Plan dynamic analysis with containment: VM snapshot, fake services, monitored filesystem/registry/process/network activity.
  4. Summarize behavior by capability: execution, persistence, privilege, defense evasion, discovery, C2, collection, exfiltration.
  5. Produce IOCs, detection logic ideas, remediation steps, and confidence levels.

Output Format

  • Summary: what the artifact appears to do.
  • Evidence: strings, APIs, paths, domains, mutexes, commands, or observed events.
  • IOCs: hashes, filenames, registry keys, network indicators, and caveats.
  • Detections: YARA/Sigma/EDR hunting ideas where appropriate.
  • Response: containment, eradication, recovery, and monitoring.

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.

Check your setup, free