Article

OWASP Top 10 for LLM Applications, explained

Aembit · aembit.io

The ten security risks unique to LLM apps, with prompt injection at number one.

Open on aembit.io ↗

The question it answers

  1. Is it safe to send customer data to AI APIs, and what about privacy laws like India's DPDP Act?

Read with it

  1. The primary source: API data is not used for training by default, with retention controls explained. openai.com Guide Enterprise privacy at OpenAI OpenAI
  2. The developer-facing detail on what is stored, for how long, and how to reduce it. developers.openai.com Guide Data controls in the OpenAI platform OpenAI
  3. The policy to quote when a customer asks whether their data trains the model. openai.com Guide How your data is used to improve model performance OpenAI
  4. Anthropic's equivalent answer, including the commercial-products carve-out. privacy.claude.com Guide Is my data used for model training? (Anthropic Privacy Center) Anthropic
  5. Covers the 7-day default retention and zero-data-retention arrangements. platform.claude.com Guide API and data retention (Claude docs) Anthropic
  6. Where to pull compliance artifacts when an enterprise customer sends a security questionnaire. anthropic.com Guide Anthropic's Transparency Hub Anthropic
eChai Partner Brands The partnership →