Loading story…
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.
Track how attackers are adapting to this technology.
4 events from the most recent confirmed update back to the earliest known activity.
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.
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.
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.
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.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
5 references tracked. Mallory keeps watching after this page renders.
discounttimu.substack.com
Open sourcesentinelone.com
Open sourcesynthesis.to
Open sourcediscounttimu.substack.com
Open sourceinfosec.pub
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
SentinelLabs introduced a multi-stage benchmark to test whether frontier AI models can autonomously sustain a full malware reverse-engineering investigation, using the 2005 **Fast16** Windows sabotage toolkit as the case study. Fast16 was designed to interfere with **LS-DYNA** engineering software and has been compared to **Stuxnet** because of its apparent link to efforts affecting Iran’s nuclear weapons development. The benchmark recreated an eight-stage investigation with staged evidence release, **IDA Pro**-based artifact generation, and verification tied to specific addresses and recovered components, including Fast16’s **Lua** framework and its 101-rule patching engine. In the reported results, **GPT-5.6 Sol** was the only publicly available model tested that completed all eight stages, while **GPT-5.5**, **GLM-5.2**, and **Opus 4.7/4.8** demonstrated useful point-in-time analysis but failed to maintain project-wide coherence. SentinelLabs said the decisive capability was **project-scale recovery**: retracting invalidated conclusions, tracing dependencies, and repairing the broader investigative narrative as new evidence emerged. The researchers concluded that current leading models can materially assist malware analysts and, in the strongest cases, operate as supervised investigative agents, but human reverse engineers remain necessary because the models still make semantic, technical, and quality-control errors and can declare completion prematurely.
Jul 23, 2026
Security researchers highlighted multiple ways **LLM adoption can introduce or amplify risk**, including both technical attacks and unsafe development practices. G DATA reported that a Git-hosted “detector” for the **Shai-Hulud worm** shipped with “test files” that were effectively *real malware*: scripts capable of deleting user directories and, in at least one case, uploading data to actual threat actors. The files were apparently intended to validate detection efficacy and may have been produced via AI-assisted “vibe coding,” where the model replicated malicious behavior one-to-one while comments claimed the code was only a simulation; although the test artifacts are not executed during normal tool operation, users could trigger damage by manually running them. Separate academic work summarized by Bruce Schneier described **side-channel attacks against LLM inference**, where data-dependent timing and token/packet-size patterns (including those introduced by efficiency techniques like speculative decoding) can leak information about user prompts even over encrypted channels. Reported impacts include inferring conversation topics with high accuracy and, in some settings, recovering sensitive data such as phone numbers or credit card numbers via active probing. In parallel, an SC Media segment discussed the operational upside of **LLM-driven secure code analysis**, citing results that improved security across hundreds of open-source projects but noting the importance of human validation and patching effort; an OSINT Team post provided a cautionary, practitioner-level example of how easily malware can be accidentally executed during analysis, reinforcing the need for disciplined handling and isolation when working with suspicious files.
Jun 29, 2026
Security researchers have identified a new wave of threats where adversaries embed Large Language Model (LLM) capabilities directly into malware, enabling malicious code to be generated at runtime and evading traditional detection methods. SentinelLABS highlighted real-world cases such as PromptLock ransomware and APT28’s LameHug/PROMPTSTEAL campaigns, noting that while these threats are adaptive, they often hardcode artifacts like API keys and prompts, which can be leveraged for detection. Novel hunting strategies, including YARA rules for API key structures and prompt detection, have uncovered thousands of LLM-enabled malware samples, including previously unknown threats like MalTerminal. In parallel, security vendors are leveraging LLMs defensively, as seen in NodeZero’s Advanced Data Pilfering (ADP) feature, which uses LLMs to identify hidden credentials and assess the business risk of compromised data. By applying semantic analysis to unstructured data, defenders can better understand what attackers might target and how to prioritize response. These developments underscore both the offensive and defensive potential of LLMs in cybersecurity, with attackers and defenders racing to exploit the technology’s unique capabilities.
Jun 29, 2026