arXiv:2606.02240v2 Announce Type: replace-cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks...
Læs hele artiklen hos kilden.
Kommentarer (0)
Ingen kommentarer ennå. Bli den første til å kommentere!