https://pypi.org/project/agentic-security-harness/ Recent updates to the Python Package Index for agentic-security-harness en https://pypi.org/project/agentic-security-harness/1.0.0/ Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests. Fri, 14 Aug 2026 18:48:17 GMT