Threats tagged 'prompt injection'

The Haiou jailbreak bundle is a prompt package targeting OpenAI Codex that weakens model guardrails for security-related tasks such as hacking and software cracking. It functions as prompt adware by modifying Codex configuration files to inject advertisements for the author's LLM gateway service into agent responses. The bundle uses techniques like role-playing, context-reframing into CTF scenarios, and refusal suppression. It was found on a misconfigured webserver alongside tools like Cobalt Strike, VulnClaw agent, and Ladon framework, indicating active use by cybercrime actors. The freely distributed jailbreak serves as a channel to promote a paid gateway service, persistently injecting promotional content through encrypted payload files distributed via GitHub and Chinese platforms.

Microsoft researchers identified a high-volume phishing campaign utilizing invisible Unicode tag characters (U+E0000 to U+E007F), a technique originally associated with AI prompt injection research known as ASCII Smuggling. The attackers inserted these invisible characters into financial keywords like 'funding' to evade email filters rather than hiding instructions from users. The campaign began February 9, 2026, generating millions of daily messages for approximately three months with a distinctive weekday-only pattern. Finance-themed disposable domains were used to send business loan and credit-line phishing through a legitimate email marketing platform. The technique, while designed for AI security contexts, proved effective at bypassing traditional keyword-based detection by splitting words with invisible characters that appear normal to recipients but break signature matches and alter ML tokenization.

A sophisticated Rust-based macOS implant named macOS.Gaslight has been discovered, featuring a novel 3.5 KB prompt-injection payload containing 38 fabricated system messages designed to disrupt LLM-assisted malware analysis. The backdoor communicates via Telegram Bot API with AES-GCM encrypted payloads over certificate-pinned TLS and includes self-redaction capabilities to hide its bot token from logs. It provides operators with an interactive shell, system information collection, and credential stealing capabilities through a bundled Python script that targets browser data, keychains, and command histories. The implant uses runtime-fetched CPython interpreters and establishes persistence through a LaunchAgent masquerading as an Apple system service. This threat is assessed with high confidence to be aligned with DPRK activity and represents a significant evolution in adversarial techniques targeting security analysts rather than sandbox environments.

Researchers disclosed 'CometJacking,' a prompt injection attack targeting Perplexity's Comet AI browser that uses a malicious URL to hijack the AI assistant and exfiltrate sensitive data such as emails and calendar entries. The attack bypasses existing data protections using simple Base64 encoding and leverages the browser's authorized access to connected services, highlighting new security risks in AI-native browsers.