threatdeck
Live 13:45 UTC ·

OWASP LLM

LLM07 · System Prompt Leakage

System prompts expose secrets, rules or internal logic that attackers extract and abuse.

OWASP Top 10 for LLM Applications (2025)

Mitigations

  • Never put credentials or access rules in prompts
  • Enforce security controls outside the model

Related techniques

In the news

  1. Attacks on AI Vulnerability arXiv (AI security papers) Medium

    Network-Exposed Configuration Attacks on LLM-Controlled Social Robots

    Researchers show an unauthenticated network attacker can replace personality and system prompt settings on a Pollen Robotics Reachy Mini Lite via its management interface (CWE-306).

    MitigateRestrict network access to the Reachy Mini Lite management interface until authentication is added

    LLM07 arXiv:2611.22761 #llm-robotics#missing-authentication#system-prompt 1 min read Brief In your stack

Mappings are AI-assisted and checked against the framework definitions; corrections welcome.

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.