Executive Summary
Underground services resell AI model access; Poison Claude offers discounted Claude access while its operator can see every customer prompt.
What Happened
Cybersecurity researchers have discovered more than half-a-dozen services advertisements for illegal access to artificial intelligence (AI) models on underground cybercrime forums and messaging platforms. One such service, Poison Claude, claims to offer access to Anthropic's large language models (LLMs), including Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6. "Advertisements for Poison Claude
Affected Products
- Anthropic Claude
Vulnerability / Attack Technique
Illicit AI access reselling with prompt interception
Technical Mechanism
A middleman proxy relays and logs prompts.
AI Security Category
LLM02:2025 Sensitive Information Disclosure
Relevant Frameworks
RealGround Analysis
Cheap unofficial AI access exposes everything users type. RealGround analysis: only use official AI endpoints.
Recommended Controls
- Block unofficial AI proxy services
- Use only approved AI providers
Related RealGround Service
AI Agent SBOM and LLM Mapping · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/08/poison-claude-sells-discounted-claude.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.