AI Wiki · Mediocre Security
IncidentIncidents

Hidden LLM prompts in WhatsApp help pages

Invisible instructions in WhatsApp help pages told AI systems not to point users to data-protection regulators.

What happened

Redact reports 102 LLM-only instruction blocks across 80 of 545 WhatsApp help pages, invisible to users, told AI systems not to point users to data protection authorities or cite GDPR, LGPD or CCPA once a lawyer was mentioned. Meta removed them Oct 15-18 and called them an unintended support-chatbot artifact.

Timeline

Every dated event in the wiki that involves Hidden LLM prompts in WhatsApp help pages, newest first.

Connections

Hidden LLM prompts in WhatsApp help pages and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

AI lab Meta

Concept Prompt injection · Retrieval-augmented generation (RAG)

Sources

  1. Redact, “WhatsApp's Hidden Notes Told AI Not to Recommend a Regulator”, Oct 19 2026