arXiv (All)
open access
AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories
LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter. A successful injection has a characteristic shape when the trajectory is read in order: a benign prefix gives way to actions that serve the
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
- Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies#299821
- ActionGuard: Tool Call Authorization under Poisoned Skills#1144417
- ActionGuard: Tool Call Authorization under Poisoned Skills#1136768
- String: An Agentic OS Where Every App Is a Markdown File#784796
- String: An Agentic OS Where Every App Is a Markdown File#783206
Record · ID 975045
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