ChatInject
[ICLR 2026] Official implementation of "ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents"
ChatInject is an indirect prompt-injection attack that exploits LLM agents' reliance on structured chat templates. By formatting malicious payloads to mimic native chat templates—and expanding to persuasion-driven multi-turn dialogues to prime the agent—ChatInject causes agents to accept and execute otherwise suspicious instructions.
⚡ How to use ChatInject
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/hwanchang00-chatinjectCapabilities
Do you own ChatInject?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.