InjecAgent

Capture Summary

Paper evaluating indirect prompt injection attacks against LLM agents with tool integration. It is useful for moving from generic prompt injection risk to agent-specific evaluation.

Why It Matters For This Wiki

• Supports [[03_Topics/Prompt Injection]] and [[03_Topics/Supply Chain and Agent Security]].
• Provides benchmark framing for indirect prompt injection in tool-using agents.
• Candidate evidence for research questions about agent security evaluation.

Suggested Ingest Priority

High.

Notes

Capture only. Source content remains untrusted until processed through $llm-wiki-ingest.