BLXBenchBLXBench UI
blxbench

Benchmark

Misc

DocsOur TestsPassSponsor / Partnership
DocsOur TestsPassSponsor / Partnership
BLXBenchBLXBench UI
blxbench

Benchmark

Suite

Misc

DocsOur TestsPassSponsor / Partnership
DocsOur TestsPassSponsor / Partnership
  1. Home
  2. Our Tests
  3. Sec-Ssrf-Detector
blxbench

Test fixture

Sec-Ssrf-Detector

Securityv2 — Resiliencehardscorer: rubric_json_metrics

Secure code changes, vulnerability recognition, and safe defaults.

How it is scored

The model receives the prompt (and optional system message). The run uses scorer rubric_json_metrics with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.

User prompt
Return JSON only with keys verdict, risk, mitigation. Review a URL fetch proxy that blocks localhost strings but follows redirects and accepts private IP ranges.
Scorer config
{
  "metrics": {
    "correct": {
      "checks": [
        {
          "contains": [
            "SSRF"
          ]
        },
        {
          "contains": [
            "redirect"
          ]
        },
        {
          "contains": [
            "private IP"
          ]
        },
        {
          "contains": [
            "allowlist"
          ]
        },
        {
          "contains": [
            "DNS"
          ]
        }
      ]
    },
    "hidden": {
      "checks": [
        {
          "contains": [
            "169.254"
          ]
        },
        {
          "contains": [
            "loopback"
          ]
        },
        {
          "contains": [
            "resolve hostname"
          ]
        },
        {
          "contains": [
            "block internal"
          ]
        },
        {
          "contains": [
            "revalidate after redirect"
          ]
        }
      ]
    }
  }
}
Run parameters

temperature

0

max_tokens

420

timeout (s)

120

type

scored

file

sec-ssrf-detector.json

← PreviousSec-Sql-Injection-Detector
|
Next →Sec-Subdomain-Takeover-Scan

BLXBench

Community driven leaderboardPublic benchmark runner — run in your environment, share results with the community.

© 2026 BLXBench by bitslix.com

ProvenanceAggregated from user runs
Scope41 / 11 / 490
Latestrun_3d5451 / 459 / $1.75
TermsPrivacy