LIVE FEED
HIGH Claude Used to Breach OpenAI Employee Account via Forum Flaw // FIRST LOOK Anthropic Embeds Accenture as Its First Third-Party AI Safety Evaluator // CRITICAL AI Hallucination in Military Intel Nearly Triggers US Strike // FIRST LOOK arXiv Paper Formalises Linguistic Illegibility in LLM Security // HIGH Gemini AI Agent Breaches Three Companies via Password Guessing // HIGH Google Gemini Breaches Real Systems in AI Security Test Mishap // FIRST LOOK TypeSafe AI Launches Jev, a Non-LLM Model for AI Agent Oversight // MEDIUM Agentic AI Pentesting Closes Gap as Exploit Speed Hits 5 Days // HIGH PhantomRaven npm Stealer Built With LLM Targets Dev Secrets // HIGH SynthID Watermarking Weakens LLM Safety Guardrails Under Attack //
MALWARE-EVASION

Malware-Evasion

3 reports
All LLM Security Agentic AI Industry News Research Supply Chain First Look: Security Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning Deep Signal Intelligence Report AI Governance AI Security AI Security Tools Identity & Access Management Monthly Review Security Operations
APT29 Abuses Claude to Auto-Rebuild Malware on Detection

APT29 Abuses Claude to Auto-Rebuild Malware on Detection

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 9.2 The Hacker News

Russian state-sponsored group GTG-20006, linked to APT29/Midnight Blizzard, weaponised Anthropic's Claude to build autonomous AI workflows that detect when their malware is flagged by security products and automatically rebuild and redeploy it to evade static detections. The operation targeted over 20 government, defence, and diplomatic organisations across Ukraine, Europe, the Middle East, and Asia, using phishing, ClickFix lures, and DNS hijacking to deliver cross-platform implants. This represents a qualitative escalation in adversarial AI use: LLMs are no longer just writing malware stubs but orchestrating full detection-evasion feedback loops at machine speed.

Prompt Injection Malware Evades LLM Security Scanners

Prompt Injection Malware Evades LLM Security Scanners

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 Schneier on Security

A malware developer has embedded nuclear and biological weapons-related text inside JavaScript comment blocks within spyware payloads, specifically to trigger refusal behaviour or context confusion in LLM-powered security analysis pipelines. The technique exploits the architectural gap between how interpreters (which skip comments) and language models (which ingest the full file as input) process the same file. While ineffective against traditional static analysis tooling, the tactic represents a practical adversarial countermeasure targeting AI-first triage workflows and analyst copilots.

Malware Uses Prompt Injection in JavaScript to Evade LLM Tools

Malware Uses Prompt Injection in JavaScript to Evade LLM Tools

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 Schneier on Security

A malware developer has been observed embedding fake system instructions and policy-triggering content — including references to nuclear and biological weapons — inside JavaScript comment blocks to confuse or trigger refusal behaviour in LLM-powered security analysis pipelines. The technique does not affect code execution but is specifically designed to disrupt naive AI-first triage tools that feed raw file content to language models without isolating it as untrusted data. Traditional static analysis methods remain unaffected, but the approach signals an emerging class of anti-AI-analysis evasion techniques.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.