Developers Build 5KB Pure-JavaScript Headless Browser to Bypass DuckDuckGo AI Chat Anti-Bot System
A team of developers has constructed a fully functional headless browser using only 5,408 bytes of obfuscated JavaScript to defeat DuckDuckGo’s anti-bot protection on its free AI chat service duck.ai.
The project began after repeated 500 errors containing the message “no x-vqd-hash-1 token” appeared while building a Telegram proxy bot. The researchers reverse-engineered four rotating challenge variants delivered inside the x-vqd-hash-1 response header, each containing heavily obfuscated JavaScript that must be executed to produce a valid proof-of-browser token.
Challenge Mechanics
Upon receiving the challenge, the synthetic browser performs environment checks that include:
- Verification that native functions contain the string “[native code]”
- Subclassing behavior of Array objects under V8
- Correct normalization of malformed HTML5 markup such as “<p><div></p><p></div”
- iframe contentWindow properties and prototype chain integrity for HTMLDivElement, HTMLElement, and Element
Results are combined with a fabricated stack trace and execution duration metadata, then hashed with a pure-JavaScript SHA-256 implementation before being returned in the same header.
Telegram Bot Capabilities
The resulting serverless Telegram bot supports ten live models, progressive message editing for streaming responses, automatic image generation via the GenerateImage tool, and JPEG-to-PNG conversion for vision requests—all without any external libraries. A dedicated SQLite table persists solved challenge tokens across function invocations.
The authors note that the entire client, including a custom HTML5 parser and DOM mannequin, fits comfortably inside a single 950-line JavaScript file that runs identically in Node.js and lightweight serverless isolates.
Related articles
Deepfake Videos for Business Attacks Drop to Just $5 per Minute as AI Costs Plummet
The cost of creating convincing deepfake videos for attacks on companies has fallen roughly 100 times over the past two years. A single minute of high-quality fake video can now be produced for as little as $5, compared with several hundred dollars previously. The drop in prices was reported by Russian newspaper Izvestia, which also noted that underground marketplaces now sell ready-made templates that further reduce expenses. Lower prices significantly lower the barrier for criminals to conduct business email compromise and CEO impersonation scams. Experts warn that recognizable faces combined with urgent requests for wire transfers or credential sharing make traditional verification methods less reliable. Organizations are advised to confirm all financial instructions through an independent, pre-established channel rather than relying on video calls alone.
Over a Dozen AI Platforms Breached in One Month for API Keys in LLM-Jacking Operations
Between late September and early November, at least a dozen AI developer platforms were compromised in a coordinated campaign targeting API access tokens rather than customer data. Affected organizations include Andromeda, NVIDIA Brev, CommandCode, Fireworks AI, Lightning AI, Northflank, OpenCode, Railway, Trigger.dev, Warp, Zeabur, Chainstack, and WorkOS. Attackers exploited third-party components and internal sales applications to reach stored credentials used for AI inference services. The stolen tokens enable LLM-jacking and model distillation activities, with multiple threat groups observed reusing the same credentials shortly after disclosure. The open-source penetration testing framework Artex was used to automate reconnaissance and exploitation, lowering the barrier for less skilled actors. Companies such as Chainstack and WorkOS confirmed the incidents through their own disclosures, highlighting risks in non-core systems that store high-value AI credentials.
NIST Publishes Draft Taxonomy SP 2400-102 for Attacks on AI Agents
The National Institute of Standards and Technology released the first public draft of SP 2400-102 E2026 on 9 November 2026, extending its 2025 machine learning attack taxonomy with a dedicated chapter on AI agents. The document provides a common terminology for attacks targeting task formulation, planning, tool execution, and result interpretation stages. Attack goals include availability disruption through infinite tool calls, integrity violations that alter outputs or trigger unauthorized actions, sensitive data disclosure, and malicious agent misuse. Vectors range from direct user prompt bypasses and supply-chain model poisoning to indirect prompt injection via untrusted documents, persistent memory poisoning, compromised tools, and inter-agent message spoofing. NIST also examines layered defenses combining model-level detection of parasitic instructions with system-level restrictions, tool isolation, and human confirmation for high-impact operations. The draft references OWASP LLM03:2026 Excessive Agency and aligns with Russian standards GOST R 56939-2024 and GOST R 59276-2020 for testing and trust evaluation. Comments are accepted until 18 December 2026 before final publication.
Fake ITSM Tickets Allow Attackers to Trick AI SOC Agents into Dismissing Real Incidents
An experiment with the DeepSeek model showed that AI agents in Security Operations Centers can be reliably deceived by forged change-management tickets rather than classic prompt injection. Attackers with limited rights edit already-approved tickets in an ITSM system, changing the server and maintenance window while preserving the “Approved” status. The agent reads the ticket, matches the observed actions to the documented work, and automatically closes the alert. Human analysts reviewing the closed case later see only the reassuring link to the ticket and may also accept the decision. Three common LLM-based defenses—strict prompting, a secondary critic model, and supplying audit logs—either blocked too many legitimate changes or still allowed a quarter of attacks through. Only a deterministic code gate that cross-checks the ticket against immutable logs, role directories, and time windows achieved zero false closures on the test set while still automating 97 percent of genuine maintenance events.