Red Teaming OpenAI and Anthropic Agent Builder Platforms
Agents that take real actions demand red teaming methods fundamentally different from chatbots.
Derek Tso
Staff Writer
Derek Tso
Derek has covered offensive security tooling and red team operations since the late 2000s, first as a practitioner and then as a journalist embedded with several bug-bounty programs. He now applies that experience exclusively to AI system assessments and autonomous agent threat modeling.
3 stories
System Prompt Confidentiality Leakage in Enterprise LLMs
System prompts containing secrets are mathematically extractable by design.
Derek Tso
Prompt Injection Defense Gaps in OWASP LLM Top 10
OWASP's defenses miss indirect, agentic, and adaptive injection attacks.
Derek Tso