Agentic AI Defense: Decode-Time Provenance Binding for MCP↗ (원문, 새 창)

본문 미리보기

arXiv:2610.31974v1 Announce Type: new Abstract: Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate cross-modal trust laundering, in which instructions concealed in an email-signature image using least-significant-bit (LSB), discrete cosine transform (DCT), or metadata steganography bypass text scanners and enter a multi-agent workflow when decoded by a tool. To counter this threat, we propose decod