Skip to content
LLMGaurd
ai.sec
home
research
products
contact
early access
[#]
topic / agents
Agents.
1 entry on agents.
All research
.
2026-09-26
Indirect prompt injection: when your agent obeys the wrong text
Why agents that read emails, web pages, and documents can be steered by attackers who never talk to them, and the architecture patterns that limit the damage.
prompt injection
agents
3 min
→