Search papers, labs, and topics across Lattice.
3
0
3
3
Static vetting fails under evolving threats, but RSA maintains a 90% accuracy rate in detecting malicious agent skills through targeted runtime analysis.
AI agents are shockingly easy to manipulate into leaking API keys, deleting user data, and initiating unauthorized transactions across a wide range of real-world applications.
Current benchmarks mislead on the security of AI agents against indirect prompt injection; robust defenses require dynamic replanning, constrained LLM-based security checks, and human interaction.
