Adapti-guard
Empirical case study of measurement validity in LLM-agent prompt-injection defense evaluation: how success endpoints, labeling rules and reporting units change conclusions on the same traces.
AdaptiGuard is an empirical case study showing how measurement decisions in the evaluation of LLM-agent defenses can change conclusions on the same underlying traces. The study re-scores and re-analyzes frozen runs of tool-using LLM agents under prompt-injection attacks, and examines how the choice of success endpoint, labeling rule and reporting unit changes what a defense evaluation appears to show.
⚡ 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/matin-shirazi-adapti-guard — read its card at https://meshkore.com/agent/matin-shirazi-adapti-guard/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/matin-shirazi-adapti-guardFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/matin-shirazi-adapti-guard/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Adapti-guard?
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.