feat: implement MCP red teaming test suite v2 with automated scripts, logging, and comprehensive evidence documentation.

scripts/run_v2_h01h02.py

@@ -0,0 +1,39 @@
+"""Re-run H01 and H02 only, with fixes for overlay and PDF timeout."""
+import sys
+import json
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent / "src"))
+from client_v2 import load_env, load_accounts, load_testcases_v2, run_full_suite_v2
+
+def main():
+    env = load_env()
+    accounts = load_accounts()
+    testcases = load_testcases_v2()
+
+    # Filter to H01 and H02 only
+    target_ids = {"H01", "H02"}
+    testcases = [tc for tc in testcases if tc["id"] in target_ids]
+
+    sys.stderr.write(f"Re-running {len(testcases)} tests (H01 + H02)...\n")
+
+    results = run_full_suite_v2(
+        accounts=accounts,
+        testcases=testcases,
+        env=env,
+        headless=True,
+        timeout_per_test=180,
+    )
+
+    # Save results separately
+    out_path = Path(__file__).parent / "reports" / "suite_results_v2_h01h02.json"
+    out_path.write_text(json.dumps(results, indent=2, ensure_ascii=False), encoding="utf-8")
+    sys.stderr.write(f"Results saved to {out_path}\n")
+
+    for r in results:
+        status = "OK" if not r.get("error") else "ERR"
+        resp_preview = r.get("response", "")[:100].replace("\n", " ")
+        sys.stderr.write(f"  [{status}] {r['id']}: {resp_preview}...\n")
+
+if __name__ == "__main__":
+    main()