INSPECTING ARCHIVED INTELLIGENCE (OUTDATED VERSION).

Aoki Infostealer Targets AI Coding Assistant Credentials Stealing Operation

| 2026-10-15 13:00 LOW HIGH DATA BREACH MALWARE & BOTNETS
Executive Summary
AI-generated
A new version of the Aoki infostealer, discovered by Symantec's Threat Hunter Team on October 15, 2026, is targeting credential and session files used by popular AI coding assistants. The attackers are able to access API keys and tokens from Anthropic’s Claude, OpenAI's Codex, SpaceX’s Cursor, Google’s Gemini, GitHub Copilot, JetBrains AI Assistant, Kiro, and Amazon Web Services (AWS). This allows them to bypass safeguards that assume requests originate from a trusted user and carry out malicious activity under a legitimate developer's identity. The infostealer has stolen tokens for these services, exposing connected repositories, cloud services, and continuous integration and delivery pipelines linked to the affected accounts.
Technical Mitigations AI-generated
• Patch Aoki infostealer versions targeting .<a href="/auth/login?next=/detail/NTo-Q6EBDYL3N98kPCCV" class="ioc-censored-pill text-decoration-none" title="Protected IoC: Sign in to view" data-bs-toggle="tooltip"><span class="badge bg-black text-warning border border-warning border-opacity-75 font-monospace ioc-lock-tag align-middle"><i class="bi bi-lock-fill me-1"></i>[IOC HIDDEN &bull; LOGIN REQUIRED]</span></a>, Claude desktop cookies, ChatGPT cookies, and the Codex config.toml and .env files to prevent credential theft. • Implement token validation for GitHub Copilot, Cursor, Gemini, JetBrains AI Assistant, Kiro, and AWS credentials to detect unauthorized access attempts. • Monitor API key usage patterns for Anthropic’s Claude, OpenAI's Codex, SpaceX’s Cursor, and Google’s Gemini to identify potential LLMjacking activities.
Technical Observables Login Required
Indicators of Compromise (IoCs) Protected

Raw threat telemetry, malicious IP addresses, file hashes, and direct VirusTotal correlation are restricted to authenticated users.

cl•••••.json
Intelligence Metadata
Actors / Malware / CVEs / Campaigns
Target & Sectors
Global Scope cryptocurrencycryptocurrency technologytechnology
Incident Timeline
‎October 15
Threat actors using the Aoki infostealer targeted credentials of users who interacted with ChatGPT, Claude, and GitHub Copilot.
tactic T1589.001 - Credentials
organisation Aoki Targets
‎2026/10/15
AI Credentials Increasingly Valuable to Hackers The researchers said Aoki’s development suggests that AI credentials are now considered just as valuable as payment card data and cryptocurrency wallets by threat actors.
infrastructure Cursor
organisation API
organisation Google
organisation GitHub Copilot
organisation JetBrains AI
organisation New Aoki Infostealer Targets AI Coding
organisation Aoki
organisation CI
Tactical Metrics
Metrics
infrastructure
‎Cursor
Affected Product
Intelligence Sources
Infosecurity-Magazine 2026-10-15