Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation.
Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.
arXiv:2607. 17986v1 Announce Type: cross Abstract: Self-hosted AI agents read and write their own memory and configuration files to function.
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
arXiv:2607. 14611v1 Announce Type: cross Abstract: A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases.
arXiv:2607. 27080v1 Announce Type: cross Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist.
arXiv:2607. 01919v1 Announce Type: new Abstract: Agentic systems enhance their capabilities by invoking external tools and maintaining persistent memory.
arXiv:2607. 26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.