Open_Ultra_SAST/benchmarks/measurements/2026-10-07-search-first-cluster-demonstration/record.json

{
  "record": "2026-10-07 FIRST CLUSTER DEMONSTRATION for search-with-proof",
  "pair": {
    "index": 13,
    "repo": "hanxi/xiaomusic",
    "family": "path",
    "class": "prefix-check-bypass (startswith without separator)",
    "language": "python"
  },
  "image": "ghcr.io/norandom/ousast-search-task@sha256:e2c8b460...",
  "side": "vulnerable",
  "outcome": "demonstrated",
  "verify_tasks": 18,
  "model_calls": 55,
  "settled_usd": 0.3686,
  "wall_seconds": 2170,
  "false_proofs_fixed_side": 0,
  "demo_wires_served_root": true,
  "finding": "The agent autonomously produced a demonstrated finding on a real CVE fix-pair end to end on the kube-ax cluster: it found the prefix-bypass sink, wired the app's served directory to ${served_root} (prompted by the new served-root control-signal hint after an earlier mis-wire), targeted the oracle's prefix-sibling canary, and the differential verifier confirmed the owned effect on the vulnerable revision and its absence on the fixed revision. Cost $0.37, 55 model calls.",
  "fix_chain_that_enabled_it": [
    "parity: agent targets the observable",
    "verify-time-only: no explore reachability trap",
    "fair-share budget: authors+verifies within budget",
    "served-root guidance: wire the served dir to ${served_root}",
    "oracle prefix-bypass coverage: sibling canary for startswith-without-separator vulns",
    "control-signal feedback: served-root hint so the agent self-corrects wiring"
  ],
  "both_sides": {
    "vulnerable": {
      "outcome": "demonstrated",
      "settled_usd": 0.3686,
      "verify_tasks": 18,
      "model_calls": 55
    },
    "fixed_blind_negative": {
      "outcome": "inconclusive",
      "false_proof": false,
      "settled_usd": 0.5632,
      "verify_tasks": 18,
      "model_calls": 85,
      "note": "Agent searched the FIXED (safe) revision blind (no vuln knowledge); authored demos but the verifier found no effect -> no false proof (Req 6.3 negative)."
    },
    "pair_total_settled_usd": 1.224,
    "verdict": "True positive on the vulnerable revision, zero false proof on the fixed revision."
  }
}