Attackers can pre-register resource names that LLMs predictably hallucinate, turning agentic AI assistants into unwitting consumers of malicious promptware payloads.
Investigating security implications of automatically generated code on the software supply chain.arXiv preprint arXiv:2509.20277, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting
Attackers can pre-register resource names that LLMs predictably hallucinate, turning agentic AI assistants into unwitting consumers of malicious promptware payloads.