{
  "run_id": "andriikhanin--mcp-agent-security-test-suite-claude-haiku-5-5-1793199739896026287",
  "date": "2026-10-28T15:17:54.935170+00:00",
  "repo": "andriikhanin/mcp-agent-security-test-suite",
  "kind": "repo",
  "source": "https://github.com/andriikhanin/mcp-agent-security-test-suite",
  "commit": "a47087ae78c3b2997b3f9f1b4a4b04a7fc0d28c0",
  "model": "claude-haiku-5-5",
  "model_version": "claude-haiku-5-5",
  "test_version": "readme-d4a8901037d734bcdd4b318322df53ccb2aac827bfa5cfe1a49a6d3bd922743d",
  "pass": null,
  "outcome": "too_slow",
  "time_to_working_s": null,
  "total_s": 935.0390720367432,
  "steps": [
    "cd <guest-path> && ls -la && cat README.md | head -c 7000; echo; python3 --version; git status 2>&1 | head -3",
    "cd <guest-path> && grep -n -i \"^#\\|npm \\|node \\|node>=\\|Node.js 2\\|quickstart\\|npm test\" README.md | head -120; echo ---; cat package.json; echo ---; node --version; npm --version; ls .coldpass",
    "cd <guest-path> && sed -n 608,628p README.md",
    "cd <guest-path> && node src/cli.mjs --version; echo \"rc=$?\"; node src/cli.mjs demo | head -c 1500; echo; echo \"demo rc=${PIPESTATUS[0]}\"; node examples/offline-ci-check.mjs | head -c 800; echo \"ci rc=${PIPESTATUS[0]}\"",
    "cd <guest-path> && (npm test 2>&1 | tail -15); echo \"npm test rc=${PIPESTATUS[0]}\"; node src/cli.mjs --help | head -c 1200; echo; echo \"help rc=${PIPESTATUS[0]}\"",
    "cd <guest-path> && node --test 2>&1 | grep -n \"^not ok\\|^    not ok\\|^  not ok\" | head; node --test > /tmp/nt.log 2>&1; echo \"rc=$?\"; grep -n -A12 \"^not ok\" /tmp/nt.log | head -60",
    "cd <guest-path> && nohup sh -c 'node --test > /tmp/nt.log 2>&1; echo \"EXIT=$?\" >> /tmp/nt.log' >/dev/null 2>&1 &\necho started"
  ],
  "stuck_step": "/bin/bash -c 'o=$(mktemp);e=$(mktemp);/bin/bash --noprofile --norc -c \"$1\" </dev/null >\"$o\" 2>\"$e\";c=$?;cat \"$o\";cat \"$e\" >&2;rm -f \"$o\" \"$e\";exit $c' coldpass 'exec /usr/bin/env -i USER=agent LOGNAME=agent USERNAME=agent <email> '\"'\"'GIT_AUTHOR_NAME=Coldpass Cold Agent'\"'\"' <email> '\"'\"'GIT_COMMITTER_NAME=Coldpass Cold Agent'\"'\"' <email> GIT_CONFIG_NOSYSTEM=1 GIT_CONFIG_SYSTEM=/dev/null GIT_CONFIG_GLOBAL=/dev/null GIT_CONFIG_COUNT=4 GIT_CONFIG_KEY_0=user.name '\"'\"'GIT_CONFIG_VALUE_0=Coldpass Cold Agent'\"'\"' GIT_CONFIG_KEY_1=user.email <email> GIT_CONFIG_KEY_2=user.useConfigOnly GIT_CONFIG_VALUE_2=true GIT_CONFIG_KEY_3=credential.helper GIT_CONFIG_VALUE_3= HOME=<guest-path> PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin LANG=C.UTF-8 SHELL=/bin/bash <env-var>=<guest-path> XDG_CONFIG_HOME=<guest-path> NPM_CONFIG_CACHE=/var<guest-path> PIP_CACHE_DIR=/var<guest-path> CARGO_HOME=/var<guest-path> GOCACHE=/var<guest-path> GOMODCACHE=/var<guest-path> CDP_URL=http://<internal-ip>:9226 <env-var>=http://<internal-ip>:9226 /bin/bash --noprofile --norc -c '\"'\"'cd <guest-path> && cd <guest-path> && nohup sh -c '\"'\"'\"'\"'\"'\"'\"'\"'node --test > /tmp/nt.log 2>&1; echo \"EXIT=$?\" >> /tmp/nt.log'\"'\"'\"'\"'\"'\"'\"'\"' >/dev/null 2>&1 &\necho started'\"'\"''",
  "error_excerpt": "exceeds time budget",
  "what_it_did": null,
  "suggested_fix": "Inspect the last guest command and installer output; prefer the smallest documented setup and useful operation for the next attempt.",
  "tokens_in": null,
  "tokens_out": null,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "Review signals: 154 sensitive read. 2 static matches retained as context.",
    "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written; read only test files inside the test workspace or its temporary folders.",
    "findings": [
      {
        "kind": "sensitive-read",
        "count": 154,
        "note": "A repository process attempted to read this sensitive path.",
        "location_count": 154,
        "process_count": 157
      }
    ],
    "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-claude-haiku-5-5-1793199739896026287",
    "evidence_file": "/data/safety/andriikhanin--mcp-agent-security-test-suite-claude-haiku-5-5-1793199739896026287.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": null,
  "agent_runtime_version": null,
  "tool_transport": null,
  "platform": "linux",
  "reasoning": "low",
  "service_tier": null,
  "resources": null,
  "native_tool_calls": null,
  "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": "claude-haiku-5-5",
    "reasoning": "low"
  },
  "fault": {
    "owner": "unknown",
    "status": "pending",
    "reason": "exceeds time budget"
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": null,
  "tool_calls": 7,
  "guest_setup": null,
  "runtime": null,
  "runtime_version": null,
  "runtime_revision": null,
  "source_revision": null,
  "evidence_version": null,
  "failure_origin": null,
  "evidence_strength": "nothing_checked",
  "works": "untested",
  "install_s": null,
  "first_use_s": null,
  "mcp": "none",
  "needs": [],
  "needs_which": null,
  "agent_interface": [],
  "license": "MIT",
  "repo_url": "https://github.com/andriikhanin/mcp-agent-security-test-suite",
  "cost_to_try": null,
  "hardware": null,
  "what_failed": "exceeds time budget",
  "local_or_hosted": "local",
  "cycle_checks": null,
  "claims": null,
  "claims_note": null,
  "example_checks": null,
  "does_what_it_says": null,
  "maintenance": {
    "last_commit_at": "2026-10-28T14:59:18Z",
    "commits_90d": 165,
    "merged_prs_90d": 158,
    "open_issues": 13,
    "open_prs": 0,
    "reply_share": null,
    "reply_threads": 0,
    "median_reply_hours": null,
    "last_release_at": null,
    "archived": false,
    "verdict": "maintained",
    "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"
  },
  "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": "README metadata",
      "observed": false,
      "operation_checked": false
    }
  ],
  "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": "2026-10-28T15:17:54.935170+00:00",
  "tested_commit": "a47087ae78c3b2997b3f9f1b4a4b04a7fc0d28c0",
  "tested_with": {
    "agent": null,
    "agent_version": null,
    "model": "claude-haiku-5-5",
    "model_route": "claude-haiku-5-5",
    "reasoning": "low",
    "os": "linux",
    "backend": "hyperv",
    "transport": null
  },
  "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": "claude-haiku-5-5",
    "model_version": "claude-haiku-5-5",
    "agent_execution": "native_agent",
    "agent_runtime": null,
    "agent_runtime_version": null,
    "tool_transport": null,
    "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": null,
    "resources": null,
    "operation": null,
    "operation_scope": null,
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-d4a8901037d734bcdd4b318322df53ccb2aac827bfa5cfe1a49a6d3bd922743d",
    "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-claude-haiku-5-5-1793199739896026287.txt",
  "report_url": "/reports/andriikhanin--mcp-agent-security-test-suite-claude-haiku-5-5-1793199739896026287.json"
}