Injecting one poisoned playbook into security knowledge sources causes systematic behavior changes in RAG AI agents across multiple LLMs and tasks, explained by a Verification Boundary classification.
arXiv preprint arXiv:2601.09129 (2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents
Injecting one poisoned playbook into security knowledge sources causes systematic behavior changes in RAG AI agents across multiple LLMs and tasks, explained by a Verification Boundary classification.