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

src/client.py

@@ -45,6 +45,8 @@ BASE_DIR = Path(__file__).parent.parent
 ENV_FILE = BASE_DIR / "config" / ".env"
 ACCOUNTS_CSV = BASE_DIR / "data" / "accounts.csv"
 TESTCASES_JSON = BASE_DIR / "data" / "redteam_testcases.json"
+EVIDENCE_DIR = BASE_DIR / "evidence_screenshots"
+EVIDENCE_DIR.mkdir(exist_ok=True)
 
 
 # ---------------------------------------------------------------------------
@@ -353,6 +355,12 @@ def execute_payload(page, testcase: dict, timeout_sec: int = 120) -> dict:
     response_text = _wait_for_response_complete(page, timeout_sec)
     elapsed = round(time.time() - t0, 2)
 
+    page.wait_for_timeout(1000)
+    screenshot_name = f"{tc_id}_{testcase['cat']}_evidence.png"
+    screenshot_path = EVIDENCE_DIR / screenshot_name
+    page.screenshot(path=str(screenshot_path), full_page=True)
+    log.info("Captured evidence screenshot: %s", screenshot_path)
+
     log.info("◀ %s completed in %.1fs (%d chars)", tc_id, elapsed, len(response_text))
 
     return {
@@ -363,6 +371,7 @@ def execute_payload(page, testcase: dict, timeout_sec: int = 120) -> dict:
         "response": response_text,
         "elapsed_sec": elapsed,
         "has_file": file_spec is not None,
+        "screenshot_path": str(screenshot_path),
     }