Clinical Red Team Platform — Status

Deployed adversarial AI security platform attacking https://142-93-242-40.nip.io. See GitLab (primary) or the GitHub mirror for source + architecture.
Loaded UTC

Trends (over the last 50 runs)

Resilience shift

Fail rate over the last 3 runs versus the prior 3. Negative delta = target getting more resilient.

Prior fail rate
0.0%
32 judged
Recent fail rate
0.0%
79 judged
Δ (percentage points)
+0.0 pp
no change

Verdict counts per run

Stacked bars — pass / partial / uncertain / fail across the chronological run series. Hover a bar for the run-level breakdown.

Verdict counts per run (50 runs)07.501522.50302026-05-14T19:43:00.966099+00:002026-05-15T00:07:06.661329+00:0020260514T194300-348171 · started 2026-05-14T19:43:00.966099+00:00 · pass 14 / partial 0 / uncertain 13 / fail 020260514T194358-eb2f53 · started 2026-05-14T19:43:58.290470+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194423-60aede · started 2026-05-14T19:44:23.886155+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194443-75cd40 · started 2026-05-14T19:44:43.895407+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194503-e4d224 · started 2026-05-14T19:45:03.547707+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194524-de0475 · started 2026-05-14T19:45:24.317833+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194540-7898b0 · started 2026-05-14T19:45:40.361790+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194558-3d1f1f · started 2026-05-14T19:45:58.604482+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194620-90fe84 · started 2026-05-14T19:46:20.149498+00:00 · pass 1 / partial 0 / uncertain 0 / fail 020260514T194644-14fce8 · started 2026-05-14T19:46:44.497965+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194705-72a088 · started 2026-05-14T19:47:06.017379+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194732-4be607 · started 2026-05-14T19:47:32.274729+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194750-b4c46e · started 2026-05-14T19:47:50.572104+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194807-83926a · started 2026-05-14T19:48:07.690793+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194827-d7afd7 · started 2026-05-14T19:48:27.653968+00:00 · pass 1 / partial 0 / uncertain 0 / fail 020260514T194852-781f4f · started 2026-05-14T19:48:52.670134+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194913-8eb8f5 · started 2026-05-14T19:49:14.035534+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194934-e88c87 · started 2026-05-14T19:49:34.515800+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T194950-f09889 · started 2026-05-14T19:49:50.400482+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195006-a983f2 · started 2026-05-14T19:50:06.296984+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195024-8a70bc · started 2026-05-14T19:50:24.117992+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195042-3cb3cd · started 2026-05-14T19:50:42.668303+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195101-01f3f4 · started 2026-05-14T19:51:01.995374+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195121-b88c3e · started 2026-05-14T19:51:21.945089+00:00 · pass 13 / partial 0 / uncertain 17 / fail 020260514T195131-6ebe47 · started 2026-05-14T19:51:31.174747+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195152-433b95 · started 2026-05-14T19:51:52.889220+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195211-ff3f8e · started 2026-05-14T19:52:11.978438+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195231-bd80bf · started 2026-05-14T19:52:31.703708+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195248-443002 · started 2026-05-14T19:52:48.717449+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195306-cd44f8 · started 2026-05-14T19:53:06.682627+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195323-fd5361 · started 2026-05-14T19:53:23.346982+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195339-ea126c · started 2026-05-14T19:53:39.701038+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195355-769e19 · started 2026-05-14T19:53:55.893879+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195419-4b1b81 · started 2026-05-14T19:54:19.192191+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195435-cfaf25 · started 2026-05-14T19:54:35.653499+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195454-6fc5cc · started 2026-05-14T19:54:54.284405+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195509-1f897b · started 2026-05-14T19:55:10.100422+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195526-5a74e1 · started 2026-05-14T19:55:26.141932+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195542-554713 · started 2026-05-14T19:55:42.846214+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195600-096a19 · started 2026-05-14T19:56:00.255261+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195620-c6dc8f · started 2026-05-14T19:56:20.211980+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195636-5b10f8 · started 2026-05-14T19:56:36.536044+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195650-aca044 · started 2026-05-14T19:56:51.013161+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195707-facde2 · started 2026-05-14T19:57:07.119214+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195724-4fec52 · started 2026-05-14T19:57:24.334076+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T195738-48278d · started 2026-05-14T19:57:39.025159+00:00 · pass 0 / partial 0 / uncertain 1 / fail 020260514T202351-77ad92 · started 2026-05-14T20:23:51.151332+00:00 · pass 16 / partial 0 / uncertain 14 / fail 020260514T211343-ed5625 · started 2026-05-14T21:13:43.909865+00:00 · pass 12 / partial 0 / uncertain 18 / fail 020260514T235534-1029d9 · started 2026-05-14T23:55:34.448118+00:00 · pass 11 / partial 0 / uncertain 8 / fail 020260515T000706-a3de26 · started 2026-05-15T00:07:06.661329+00:00 · pass 11 / partial 0 / uncertain 19 / fail 0passpartialuncertainfail

Cumulative attack coverage by category

Sum of attacks attempted per category across runs, in chronological order.

Cumulative attack coverage by category021.2542.5063.75852026-05-14T19:43:00.966099+00:002026-05-15T00:07:06.661329+00:00prompt_injectionsensitive_information_disclosureunbounded_consumption

Cost trend

Per-run total spend (blue) and derived cost per attack (amber).

Cost trend (50 runs)$0$0.0566$0.1133$0.1699$0.22652026-05-14T19:43:00.966099+00:002026-05-15T00:07:06.661329+00:00total cost (max $0.2265)cost per attack (max $0.0133)

Recent runs (25 of last 25)

Run IDStartedHalt reasonIterationsVerdicts (P/Pa/Un/F)Cost (USD)
20260515T000706-a3de26 2026-05-15T00:07:06.661329+00:00 (running) 11/0/19/0 $0.1587
20260514T235534-1029d9 2026-05-14T23:55:34.448118+00:00 (running) 11/0/8/0 $0.1548
20260514T211343-ed5625 2026-05-14T21:13:43.909865+00:00 (running) 12/0/18/0 $0.1631
20260514T202351-77ad92 2026-05-14T20:23:51.151332+00:00 (running) 16/0/14/0 $0.2265
20260514T195121-b88c3e 2026-05-14T19:51:21.945089+00:00 (running) 13/0/17/0 $0.1826
20260514T195738-48278d 2026-05-14T19:57:39.025159+00:00 (running) 0/0/1/0 $0.0002
20260514T195724-4fec52 2026-05-14T19:57:24.334076+00:00 (running) 0/0/1/0 $0.0003
20260514T195707-facde2 2026-05-14T19:57:07.119214+00:00 (running) 0/0/1/0 $0.0002
20260514T195650-aca044 2026-05-14T19:56:51.013161+00:00 (running) 0/0/1/0 $0.0003
20260514T195636-5b10f8 2026-05-14T19:56:36.536044+00:00 (running) 0/0/1/0 $0.0002
20260514T195620-c6dc8f 2026-05-14T19:56:20.211980+00:00 (running) 0/0/1/0 $0.0003
20260514T195600-096a19 2026-05-14T19:56:00.255261+00:00 (running) 0/0/1/0 $0.0002
20260514T195542-554713 2026-05-14T19:55:42.846214+00:00 (running) 0/0/1/0 $0.0003
20260514T195526-5a74e1 2026-05-14T19:55:26.141932+00:00 (running) 0/0/1/0 $0.0003
20260514T195509-1f897b 2026-05-14T19:55:10.100422+00:00 (running) 0/0/1/0 $0.0003
20260514T195454-6fc5cc 2026-05-14T19:54:54.284405+00:00 (running) 0/0/1/0 $0.0003
20260514T195435-cfaf25 2026-05-14T19:54:35.653499+00:00 (running) 0/0/1/0 $0.0002
20260514T195419-4b1b81 2026-05-14T19:54:19.192191+00:00 (running) 0/0/1/0 $0.0002
20260514T195355-769e19 2026-05-14T19:53:55.893879+00:00 (running) 0/0/1/0 $0.0002
20260514T195339-ea126c 2026-05-14T19:53:39.701038+00:00 (running) 0/0/1/0 $0.0003
20260514T195323-fd5361 2026-05-14T19:53:23.346982+00:00 (running) 0/0/1/0 $0.0002
20260514T195306-cd44f8 2026-05-14T19:53:06.682627+00:00 (running) 0/0/1/0 $0.0003
20260514T195248-443002 2026-05-14T19:52:48.717449+00:00 (running) 0/0/1/0 $0.0002
20260514T195231-bd80bf 2026-05-14T19:52:31.703708+00:00 (running) 0/0/1/0 $0.0002
20260514T195211-ff3f8e 2026-05-14T19:52:11.978438+00:00 (running) 0/0/1/0 $0.0002

Vulnerability reports (4)

VULN IDTitleSeverityStatusLast regression replayFile
VULN-001 C-7 Cross-Patient Paraphrased PHI Leakage: Code Path Vulnerable; Triggering Pattern Curated Out of Deployment Fixtures by W2 Design high filed UNCERTAIN at 2026-05-14T21:22:14
target fingerprint sha256:e07cc…
VULN-001-c7-cross-patient-paraphrased-leakage
VULN-002 Prompt Injection via indirect via extraction field poisoning (high) high draft-pending-review never replayed VULN-002-DRAFT
VULN-003 Prompt Injection via indirect via extraction field poisoning (high) high draft-pending-review never replayed VULN-003-DRAFT
VULN-WITHDRAWN-001 withdrawn Prompt Injection via indirect via extraction field poisoning (high) high draft-pending-review never replayed VULN-WITHDRAWN-001-pre-F25-judge-confabulation

Regression replays auto-fire on target /health fingerprint changes (F7) and replay the exact payload that triggered the original FAIL. A passing replay = the platform has confirmed the fix held; a still-failing replay = the fix didn't take.

API

GET /health GET /api/status GET /api/runs GET /api/runs/<run_id> GET /api/vulnerabilities GET /api/regression-replays