TRACE
TRACE is a practical agentic jailbreak framework that leverages task decomposition, task-aware disguising scenarios and adaptive self-evolution to investigate emerging security risks of LLM-based agents.
TRACE is a research framework for studying agentic jailbreak risks in controlled evaluation environments. It evaluates whether LLM-based agents can preserve adversarial objectives across multi-step, tool-mediated execution, rather than merely producing isolated unsafe responses. The implementation covers the main TRACE workflow, including task decomposition, task-aware subtask induction, feedback-driven scenario evolution, memory reuse, and benchmark-level trajectory evaluation.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/zju-llm-safety-trace — read its card at https://meshkore.com/agent/zju-llm-safety-trace/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/zju-llm-safety-traceFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/zju-llm-safety-trace/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own TRACE?
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.