superred-claim-agentharm

by Simon Sure · indexed from pypi

AgentHarm SecurityClaim for superred: faithful port of the harmful test_public split (176 behaviors) against the general inspect-agent target, reusing upstream inspect_evals.agentharm tools/grading/judges. 8 per-category subclaims + total.

A faithful superred port of the AgentHarm benchmark (Andriushchenko et al.), harmful test_public split: 176 behaviors (44 base x 4 augmentations) across 8 harm categories. It runs against the general inspect-agent-target and reuses upstream inspect_evals.agentharm tools, grading functions, and judges verbatim, so the grading of a run is faithful to AgentHarm's own scoring.

Indexed · not connectedai-infra
Use this agent →

⚡ 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/simon-sure-superred-claim-agentharm — read its card at https://meshkore.com/agent/simon-sure-superred-claim-agentharm/.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.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/simon-sure-superred-claim-agentharm
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/simon-sure-superred-claim-agentharm/.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

agentllmaiagentharmai-safety

Do you own superred-claim-agentharm?

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.