AI Incident Database #1020 · 2025-04-11
Reportedly Unsafe Deployment of Llama.cpp Reveals Interactive AI-Generated CSAM Roleplay Prompts
A study by UpGuard reports that misconfigured llama.cpp servers publicly exposed user prompts, including hundreds of interactive roleplay scenarios.
- Risk class (MIT)
- Compromise of privacy by obtaining, leaking or correctly inferring sensitive information
- Reports
- 2
- Developers and deployers named
- 2
Reports
- Sex-Fantasy Chatbots Are Leaking a Constant Stream of Explicit Messages · wired.com, 2025-04-11
- Analyzing llama.cpp Servers for Prompt Leaks · upguard.com, 2025-04-11
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.