{
  "run_id": "andriikhanin--mcp-agent-security-test-suite-gpt-6-luna-1793200609759453128",
  "date": "2026-10-28T15:19:01.479595+00:00",
  "repo": "andriikhanin/mcp-agent-security-test-suite",
  "kind": "repo",
  "source": "https://github.com/andriikhanin/mcp-agent-security-test-suite",
  "commit": "a47087ae78c3b2997b3f9f1b4a4b04a7fc0d28c0",
  "model": "gpt-6-luna",
  "model_version": "gpt-6-luna",
  "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 39.739265955999144,
  "total_s": 131.72010016441345,
  "steps": [
    "pwd; git status --short --branch; rg --files -g 'README*' -g 'pyproject.toml' -g 'package.json' -g 'requirements*.txt' -g 'Makefile' -g 'AGENTS.md' -g '.github/**' | head -80; python3 --version; sed -n '1,240p' README.md",
    "rg --files | head -20; node --version; npm --version; rg -n '^## |^```sh|^```bash' README.md | tail -60; ls -la",
    "grep -nE '^## |^```sh|^```bash' README.md | tail -70; cat package.json; ls .coldpass",
    "sed -n '608,630p' README.md; node src/cli.mjs scenario fixtures/scenario-denial.json",
    "node src/cli.mjs --help | head -15",
    "mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"node\",\"src/cli.mjs\",\"scenario\",\"fixtures/scenario-denial.json\"],\"cwd\":\"<guest-path>\",\"expected_text\":\"\\\"status\\\": \\\"PASS\\\"\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Scenario fixture produces synthetic policy results\",\"source\":\"scenario \u2014 synthetic authorization, replay, scoped resources and failure semantics\",\"input\":\"fixtures/scenario-denial.json\",\"expected\":\"PASS\",\"probe_kind\":\"cli\",\"argv\":[\"node\",\"src/cli.mjs\",\"scenario\",\"fixtures/scenario-denial.json\"],\"expected_text\":\"\\\"status\\\": \\\"PASS\\\"\",\"cwd\":\"<guest-path>\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Quickstart scenario run\",\"source\":\"README.md / Quickstart\",\"input\":\"fixtures/scenario-denial.json\",\"expected\":\"PASS\",\"argv\":[\"node\",\"src/cli.mjs\",\"scenario\",\"fixtures/scenario-denial.json\"],\"cwd\":\"<guest-path>\",\"expected_text\":\"\\\"status\\\": \\\"PASS\\\"\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"checks\":[],\"reason\":\"Inspected README entrypoints and package scripts; the documented operations are one-shot CLI contract checks, with no scheduler or recurring cycle.\"}\nEOF\n",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "sed -n '18,26p' README.md",
    "cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The tool is an offline synthetic contract-testing tool\",\"source\":\"This is an **offline synthetic contract-testing tool**\",\"input\":\"fixtures/scenario-denial.json\",\"expected\":\"PASS\",\"probe_kind\":\"cli\",\"argv\":[\"node\",\"src/cli.mjs\",\"scenario\",\"fixtures/scenario-denial.json\"],\"expected_text\":\"\\\"status\\\": \\\"PASS\\\"\",\"cwd\":\"<guest-path>\"}]\nEOF\n",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run synthetic scenario contract check\",\"operation_scope\":\"README Quickstart scenario fixture; Node.js >=20 prerequisite\",\"steps\":[\"Read README Quickstart and confirmed Node.js 22.23.4 satisfies the >=20 requirement\",\"Ran node src/cli.mjs scenario fixtures/scenario-denial.json; output reported PASS with 11 checks\",\"Saved probe, exact README claim, example and cycle assessment\",\"Validated and replayed evidence with the coldpass checker\"],\"deviations\":[\"None\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF"
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Run synthetic scenario contract check",
  "suggested_fix": null,
  "tokens_in": 169854,
  "tokens_out": 1213,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "node",
          "src/cli.mjs",
          "scenario",
          "fixtures/scenario-denial.json"
        ],
        "kind": "cli",
        "returncode": 0,
        "stdout": "{\n  \"status\": \"PASS\",\n  \"scenario\": \"access-boundaries\",\n  \"checks\": 11,\n  \"actualFinal\": {\n    \"allowed\": 2,\n    \"denied\": 9,\n    \"reads\": 1,\n    \"writes\": 1,\n    \"notes\": 1\n  },\n  \"mismatches\": [],\n[excerpt truncated]",
        "stderr": "",
        "needs_credentials": false,
        "needs_browser": false,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "No problems traced to this repository code in these checks. 2 static matches retained as context.",
    "findings": [],
    "context": [
      {
        "kind": "hardcoded-secret",
        "count": 2,
        "note": "Gitleaks found a possible hardcoded secret; value withheld.",
        "location_count": 2
      }
    ],
    "limitations": [
      "A short run cannot establish that code is safe.",
      "Connections show IP addresses; proxies can hide the final hostname.",
      "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing."
    ],
    "static": {
      "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check."
    },
    "evidence_url": "/safety/?run=andriikhanin--mcp-agent-security-test-suite-gpt-6-luna-1793200609759453128",
    "evidence_file": "/data/safety/andriikhanin--mcp-agent-security-test-suite-gpt-6-luna-1793200609759453128.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "codex",
  "agent_runtime_version": "codex-cli 0.164.0",
  "tool_transport": "mcp-assigned-vm",
  "platform": "linux",
  "reasoning": "low",
  "service_tier": "standard",
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 11,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "a47087ae78c3b2997b3f9f1b4a4b04a7fc0d28c0",
    "url": "https://github.com/andriikhanin/mcp-agent-security-test-suite"
  },
  "purpose": "initial",
  "profile": {
    "model": "gpt-6-luna",
    "reasoning": "low"
  },
  "fault": {
    "owner": null,
    "status": "resolved",
    "reason": null
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 11,
  "guest_setup": null,
  "runtime": null,
  "runtime_version": null,
  "runtime_revision": null,
  "source_revision": null,
  "evidence_version": null,
  "failure_origin": null,
  "evidence_strength": "readme_checked",
  "works": "yes",
  "install_s": null,
  "first_use_s": null,
  "mcp": "none",
  "needs": [],
  "needs_which": null,
  "agent_interface": [
    "cli"
  ],
  "license": "MIT",
  "repo_url": "https://github.com/andriikhanin/mcp-agent-security-test-suite",
  "cost_to_try": "free",
  "hardware": null,
  "what_failed": null,
  "local_or_hosted": "local",
  "cycle_checks": [
    {
      "kind": "cycle",
      "claim": "Scheduled or looping main behavior",
      "source": "repository entry points",
      "input": "source inspection",
      "expected": "identify the product trigger",
      "verdict": "yes",
      "outcome": "Inspected README entrypoints and package scripts; the documented operations are one-shot CLI contract checks, with no scheduler or recurring cycle.",
      "evidence": "Inspected README entrypoints and package scripts; the documented operations are one-shot CLI contract checks, with no scheduler or recurring cycle.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "The tool is an offline synthetic contract-testing tool",
      "source": "This is an **offline synthetic contract-testing tool**",
      "input": "fixtures/scenario-denial.json",
      "expected": "PASS",
      "command": "node src/cli.mjs scenario fixtures/scenario-denial.json",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: \"status\": \"PASS\"",
      "evidence": "\u2026\"status\": \"PASS\",\n  \"scenario\": \"access-boundaries\",\n  \"checks\": 11,\n  \"actualFinal\": {\n    \"allowed\": 2,\n    \"denied\": 9,\n    \"reads\": 1,\n    \"writes\": 1,\n    \"notes\": 1\n  },\n  \"mismatches\": [],\n  \"steps\": [\n    {\n      \"step\": 1,\n      \"decision\": \"DENY\",\n      \"reason\": \"OWNER_MISMATCH\",\n      \"effect\": \"NONE\",\n      \"outcome\": \"SUCCESS\"\n    },\n    {\n      \"step\": 2,\n      \"decision\": \"DENY\",\n      \"reason\": \"AUDIENCE_MISMATCH\",\n      \"effect\": \"NONE\",\n      \"outcome\": \"SUCCESS\"\n    },\n    {\n      \"step\": 3,\n      \"decision\": \"DENY\",\n      \"reason\": \"INSUFFICIENT_SCOPE\",\n      \"effect\": \"NO",
      "returncode": 0,
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Quickstart scenario run",
      "source": "README.md / Quickstart",
      "input": "fixtures/scenario-denial.json",
      "command": "node src/cli.mjs scenario fixtures/scenario-denial.json",
      "evidence": "n\": \"DENY\",\n      \"reason\": \"APPROVAL_REQUIRED\",\n      \"effect\": \"NONE\",\n      \"outcome\": \"SUCCESS\"\n    },\n    {\n      \"step\": 10,\n      \"decision\": \"ALLOW\",\n      \"reason\": \"AUTHORIZED\",\n      \"effect\": \"WRITE\",\n      \"outcome\": \"SUCCESS\"\n    },\n    {\n      \"step\": 11,\n      \"decision\": \"ALLOW\",\n      \"reason\": \"AUTHORIZED\",\n      \"effect\": \"READ\",\n      \"outcome\": \"SUCCESS\"\n    }\n  ],\n  \"reportSchemaVersion\": 1,\n  \"command\": \"scenario\",\n  \"exitCode\": 0,\n  \"summary\": {\n    \"failureCount\": 0,\n    \"reportedFindings\": 0,\n    \"findingsTruncated\": false,\n    \"ruleCodes\": []\n  },\n  \"guidance\": []\n}",
      "deferred": false,
      "expected": "PASS",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 165,
    "last_commit_at": "2026-10-28T14:59:18Z",
    "last_release_at": null,
    "median_reply_hours": null,
    "merged_prs_90d": 158,
    "note": "actively maintained: last commit 0 days ago; 165 commits and 158 merged PRs in 90 days; 13 open issues, 0 open PRs; no releases",
    "open_issues": 13,
    "open_prs": 0,
    "reply_share": null,
    "reply_threads": 0,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 0 days ago; 165 commits and 158 merged PRs in 90 days; 13 open issues, 0 open PRs; no releases",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago; 9 open issues, 13 answered or closed",
  "last_commit_at": "2026-10-28T14:59:18Z",
  "last_release_at": null,
  "open_issues": 9,
  "answered_issues": 13,
  "platforms_claimed": [
    "linux",
    "windows"
  ],
  "topic": "mcp-server",
  "agent_interfaces": [
    {
      "interface": "mcp",
      "evidence": "README metadata",
      "observed": false,
      "operation_checked": false
    },
    {
      "interface": "cli",
      "evidence": "independent checker",
      "observed": true,
      "operation_checked": true
    }
  ],
  "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.",
  "mcp_context": null,
  "tested_at": "2026-10-28T15:19:01.479595+00:00",
  "tested_commit": "a47087ae78c3b2997b3f9f1b4a4b04a7fc0d28c0",
  "tested_with": {
    "agent": "codex",
    "agent_version": "codex-cli 0.164.0",
    "model": "gpt-6-luna",
    "model_route": "gpt-6-luna",
    "reasoning": "low",
    "os": "linux",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "andriikhanin/mcp-agent-security-test-suite",
    "source": "https://github.com/andriikhanin/mcp-agent-security-test-suite",
    "commit": "a47087ae78c3b2997b3f9f1b4a4b04a7fc0d28c0",
    "source_revision": null,
    "os": "linux",
    "architecture": null,
    "backend": "hyperv",
    "model": "gpt-6-luna",
    "model_version": "gpt-6-luna",
    "agent_execution": "native_agent",
    "agent_runtime": "codex",
    "agent_runtime_version": "codex-cli 0.164.0",
    "tool_transport": "mcp-assigned-vm",
    "runtime": null,
    "runtime_version": null,
    "runtime_revision": null,
    "sandbox_source": null,
    "guest_setup": null,
    "source_pin": {
      "commit": "a47087ae78c3b2997b3f9f1b4a4b04a7fc0d28c0",
      "url": "https://github.com/andriikhanin/mcp-agent-security-test-suite"
    },
    "platform_details": {
      "os": "linux",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": "standard",
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Run synthetic scenario contract check",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": "/transcripts/andriikhanin--mcp-agent-security-test-suite-gpt-6-luna-1793200609759453128.txt",
  "report_url": "/reports/andriikhanin--mcp-agent-security-test-suite-gpt-6-luna-1793200609759453128.json"
}