Sealmark
Automated re-test on 2026-11-20: not checked by hand, and not yet reviewed by the maintainers.

Results / @kadmo/cli

@kadmo/cli

version tested 0.5.1npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run34 tools

Sealmark's automated test of @kadmo/cli 0.5.1 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B). None of the 34 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 10 checks, 3 passed, 1 failed, 3 inconclusive and 3 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 3 not applicable. The run used Sealmark 1.0.1 with the standard settings.

B

Grade B

The server's grade is its lowest test-area grade. How grading works

None of the 34 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

B
Protocol3/4 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 34 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server kadmo-agent 0.5.1 answered; 34 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 34 tool definition(s) and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
fail
server died on malformed input
Evidence for robust-input: 1 line
  1. Probe run_workflow: required arguments missing
    Outcome server process exited or stopped answering (MCP error -32000: MCP error -32000: The Kadmo runtime is not running: `kadmo mcp` relays to it and starts nothing itself)
    Decided from the MCP exchange (protocol) · tool run_workflow
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 1 captured response(s), 0 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
n/a
the server sent no instructions
refusal-quality (advisory)
Refusals say what to do next
n/a
no refusal was recorded in this run, so there is nothing to judge

Network checks

CheckVerdictWhat happened
net-loopback-ssrfcritical
Refuses loopback targets (SSRF)
inconclusive
the listener saw nothing, but 18 of 18 probes were not explicitly refused (18 failed without saying the target was refused), so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
net-scheme-allowlistcritical
Only http(s) schemes accepted
inconclusive
no scheme had an observable effect, but 12 of 12 scored probes were not explicitly refused, so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
net-caps
Response size and time are capped
n/a
net-loopback-ssrf was inconclusive: the server never reached the loopback listener, so no loopback URL is known to be fetchable; response size and time caps were not measured
net-redirect
Redirects are re-validated
n/a
the server refused or never reached the loopback listener, so redirect handling could not be observed (a server that blocks loopback cannot be sent a redirect it would follow)

Effects checks

CheckVerdictWhat happened
annotation-honestycritical
Read-only tools change nothing
inconclusive
every control call failed, so the read-only annotation could not be checked
openworld-honesty
Closed-world tools stay on the machine
n/a
no tool declares openWorldHint: false that could be given a harness-owned control argument
undeclared-writes (advisory)
Unannotated tools leave the sandbox unchanged
n/a
every tool carries annotations, nothing to check

Each check id links to what it tests and how to fix a failure. The same text is in sealmark explain <id>.

Under a check, Evidence shows what it probed (sent or inspected) and what it observed in this run: up to 6 lines per check, each cut at 240 characters, for checks that are not security checks. The text is shortened, and paths and anything that looks like a secret or token are replaced. Run sealmark run --format json yourself for every line in full.

By tool

Which checks called each tool with a valid call in this run, and which did not exercise it. A check can leave a tool out for several reasons: a limit Sealmark sets, a tool left out by design, input the run could not fill in, or a call that returned an error. The CLI report gives the reason. A verdict belongs to the whole check, not to one tool: a failed check that called three tools does not say which one failed. Security checks are left out of this table.

ToolCalled byNot exercised by
run_workflowNo check listed here called it with a valid call.None
get_run_logNo check listed here called it with a valid call.None
list_workflowsNo check listed here called it with a valid call.None
get_workflowNo check listed here called it with a valid call.None
list_run_logsNo check listed here called it with a valid call.None
publish_artifactNo check listed here called it with a valid call.None
publish_reportNo check listed here called it with a valid call.None
get_browser_statusNo check listed here called it with a valid call.None
capture_pageNo check listed here called it with a valid call.None
navigateNo check listed here called it with a valid call.None
snapshotNo check listed here called it with a valid call.None
clickNo check listed here called it with a valid call.None
typeNo check listed here called it with a valid call.None
press_keyNo check listed here called it with a valid call.None
scrollNo check listed here called it with a valid call.None
extractNo check listed here called it with a valid call.None
screenshotNo check listed here called it with a valid call.None
select_optionNo check listed here called it with a valid call.None
fillNo check listed here called it with a valid call.None
waitNo check listed here called it with a valid call.None
existsNo check listed here called it with a valid call.None
extract_allNo check listed here called it with a valid call.None
extract_mapNo check listed here called it with a valid call.None
scroll_into_viewNo check listed here called it with a valid call.None
hoverNo check listed here called it with a valid call.None
inject_cssNo check listed here called it with a valid call.
evaluateNo check listed here called it with a valid call.
browser_batchNo check listed here called it with a valid call.
set_basic_authNo check listed here called it with a valid call.
clear_basic_authNo check listed here called it with a valid call.
list_tabsNo check listed here called it with a valid call.
new_tabNo check listed here called it with a valid call.
close_tabNo check listed here called it with a valid call.
select_profileNo check listed here called it with a valid call.

What was not covered

Grade over time

Since the run on

Same as that run: the same grade in every test area, the same tools with the same input schemas, the same server version (0.5.1), the same Sealmark version (1.0.1).

  1. –did not run
  2. Bv0.5.1Sealmark 1.0.1
  3. Bv0.5.1Sealmark 1.0.1

Package facts

License
UNLICENSED (npm's word for no rights granted to others)
Latest release
0.5.1, published 12 Nov 2026 (the version graded on this page)

From npm, checked 22 Nov 2026. Plain facts about the package; they play no part in the grade.

Add it to an MCP client

This starts version 0.5.1, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "kadmo-cli": {
      "command": "npx",
      "args": [
        "-y",
        "@kadmo/cli@0.5.1",
        "mcp"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add kadmo-cli -- npx -y "@kadmo/cli@0.5.1" mcp

The test run started the server with no API keys or other secrets, and with a cleaned environment. If the server needs some, its own documentation says how to pass them.

Run it yourself

This repeats the run with the same Sealmark version and the standard settings, starting the server the same way:

npx -y sealmark@1.0.1 run --start "npx -y @kadmo/cli@0.5.1 mcp"

To confirm your run used the standard settings, add --format json --out report.json to the command. In the report, config.standard should be true and config.hash should start with sha256:d13e7893a0ac, as they did in this run. If either differs, so did the settings, and the verdicts may too (STANDARD and CUSTOM runs).

To keep the setup, put the start command in sealmark.yaml as the server.

Grade alerts

One email when the grade of @kadmo/cli changes after a re-test. Nothing else, and every email has a link to stop them.

Or follow it in a feed reader: the Atom feed lists each move of the overall grade that came with a different version of this server, tested with the same Sealmark version as the graded run before.

Each of 613 verdicts was checked independently, and Sealmark was wrong on some: how reliable Sealmark is.

Is this wrong?

Reply on the GitHub issue or email disclosure@sealmark.dev and we will recheck it. Maintainers can ask for their server to be removed.

If we were wrong, we correct the page and add your reply. Security findings go to the maintainer privately first; see the disclosure policy.