PromptArmor Launches FrontierBreach, an Enterprise Agent Security Benchmark
PromptArmor has launched FrontierBreach to measure attack success rates in real-world enterprise agent workflows, covering outcomes such as ransomware, data theft, and phishing. The benchmark incorporates indirect prompt-injection vectors—including untrusted files, emails, and skills—into GDPval tasks across nine industries. The attack success rate for healthcare and social assistance workflows was 44.4%, higher than the benchmark average of 34.9%.
Why read this
SelectedAI score 69
The benchmark embeds indirect prompt injection into workflows across nine industries, providing a concrete framework for comparing enterprise agents’ risk exposure across different attack chains.
Topics
Body
We wanted tasks where agents must navigate adversarial content while attempting to produce high-value deliverables.
To do this, we have pioneered both the concept of an "Attack Soul" and a synthetic injection generation technique that can be utilized with any existing evaluation benchmark.
For our flagship benchmark, we injected common delivery vectors for prompt injections (such as untrusted files, emails, and skills) for agent tasks from GDPval across all industry sectors.
AI Trends