EXP.001EXPERIMENT
RAG SECURITYIN PROGRESS
RAG Poisoning
How vulnerable are RAG systems to malicious documents?
Team NullFrame · Results not yet availableRead the research brief
RESEARCH / TEAM NULLFRAME
Understand the failure modes.
Team NullFrame studies the security of AI-native systems. We document the question, the approach, and the limits of what we know.
EXPERIMENTS
EVIDENCE BEFORE CLAIMSEXP.002EXPERIMENT
AI-BUILT SOFTWARE SECURITYPLANNED
Security Drift in Iterative AI Coding
How does repeated AI-assisted modification affect software security?
Team NullFrame · Study planned · No results yetRead the research brief
Further questions to explore.
Areas we want to explore. These are research interests, not published studies.
01
Prompt Injection
AREA OF INTEREST02
Indirect Prompt Injection
AREA OF INTEREST03
Agent Tool Abuse
AREA OF INTEREST04
AI-generated Code Security
AREA OF INTEREST05
System Prompt Security
AREA OF INTEREST06