SafeAgent is a stateful runtime protection system that improves LLM agent robustness to prompt injections over baselines while preserving task performance.
RedVisor: Reasoning-aware prompt injection defense via zero-copy KV cache reuse
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SafeAgent: A Runtime Protection Architecture for Agentic Systems
SafeAgent is a stateful runtime protection system that improves LLM agent robustness to prompt injections over baselines while preserving task performance.