Skip to main content
Mallory
← Back to News
ai-platform-securityoffensive-tooling-releasecredential-stealer-activity

Multi-Agent LLM Pipeline Improves Reliability of Automated Malware Analysis

Emerging Technology Risk · 5 sources · Updated 5mo ago · First seen Mar 19, 2026

Multi-Agent LLM Pipeline Improves Reliability of Automated Malware Analysis

SentinelOne detailed a multi-agent LLM pipeline for automated static malware analysis that uses an orchestrator and tool-specific subagents for radare2, Ghidra, Binary Ninja, and IDA Pro to examine macOS samples in sequence. The system, built on OpenClaw, keeps shared context in memory, normalizes outputs into a common schema, and routes findings to a report writer only after a second adversarial review stage known as the Gauntlet. The design favors deterministic bridge scripts over MCP-style integrations to improve repeatability, reduce latency, and support batch analysis at lower cost.

Testing on malware including SysJoker, WizardUpdate, FinderRAT, and a Go-based infostealer showed the pipeline could catch incorrect C2 paths, false Tor indicators, malformed strings, dead code, and decompiler-induced hallucinations that might otherwise appear in analyst reports. Related writeups and community discussion echoed the same conclusion: single-tool LLM malware analysis can produce authoritative-looking but unreliable results, while a serial consensus approach that anchors claims to virtual addresses and decompilation snippets can materially improve confidence in automated reverse-engineering output.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

4 events · Mar 18, 2026 – Mar 23, 2026
  1. Mar 23, 20268mo ago

    Part 2 on using a local LLM and Ghidra is published

    A follow-up post titled "Using Local LLM and Ghidra to analyze malware (Part 2)" was published. It continues the public discussion of LLM-assisted malware analysis workflows.

    Using Local LLM and Ghidra to analyze malware (Part 2)
  2. Mar 19, 20268mo ago

    SentinelOne publishes adversarial consensus engine research

    SentinelOne published research describing a multi-agent LLM pipeline for automated static analysis of macOS malware, using an orchestrator, tool-specific subagents, and a second-stage adversarial review process called the Gauntlet. The write-up says the system was tested on malware including SysJoker, WizardUpdate, FinderRAT, and a Go infostealer to reduce hallucinations and decompiler-induced errors.

    Building an Adversarial Consensus Engine | Multi-Agent LLMs for Automated Malware Analysis | SentinelOne
  3. Mar 18, 20268mo ago

    Part 1 on using LLM and Ghidra for malware analysis is published

    A post titled "Using LLM and Ghidra to analyze malware (Part 1)" was published. It represents a related public write-up on applying LLMs and Ghidra to malware analysis.

    Using LLM and Ghidra to analyze malware (Part 1)
  4. Mar 18, 20268mo ago

    Tim Blazytko publishes article on agentic malware analysis pipeline

    A post titled "Building a Pipeline for Agentic Malware Analysis" was published, describing an agentic approach to malware analysis. This marks the public appearance of the pipeline concept discussed across the references.

    Building a Pipeline for Agentic Malware Analysis | Tim Blazytko
Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.