https://pypi.org/project/superred-claim-agentharm/ Recent updates to the Python Package Index for superred-claim-agentharm en https://pypi.org/project/superred-claim-agentharm/0.1.0/ 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. info@simonsure.com Wed, 22 Jul 2026 18:03:31 GMT