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
- LLM02 Sensitive Information Disclosure OWASP LLM
- AML.T0069 Discover LLM System Information MITRE ATLAS
In the news
-
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.