arXiv (All)
open access
Agentic AI Defense: Decode-Time Provenance Binding for MCP
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Agentic AI Defense: Decode-Time Provenance Binding for MCP#1442305
- ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents#282842
- Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?#1131777
- My Credentials, Please: Detecting Filesystem Capability Laundering in MCP Servers at Scale#1357956
- My Credentials, Please: Detecting Filesystem Capability Laundering in MCP Servers at Scale#1348759
Record · ID 1447341
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive