Results / securenow
securenow
Sealmark's automated test of securenow 8.28.0 on 2026-11-20 gave it grade D, its lowest test-area grade (protocol D and effects A). Only 37 of 125 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 6 checks, 4 passed and 2 failed. 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. The grade includes a finding under private disclosure; it still counts in full.
Grade D
The server's grade is its lowest test-area grade. How grading works
The grade includes a finding under private disclosure. It still counts in full.
Only 37 of 125 tools could be called with default settings, so the deeper test areas cover only those tools.
Grade by test area
Protocol checks
| Check | Verdict | What happened |
|---|---|---|
| protocol Valid MCP handshake and tool schemas | pass | handshake ok, 125 well-formed tool(s) |
| tool-poisoningcritical No tool-poisoning indicators in tool metadata | fail | A security finding is being reported to the maintainer privately. Details will be published when it is fixed or 90 days after the report (disclosure policy). |
| robust-input Survives malformed tool input | fail | server died on malformed input |
| secret-echocritical No environment secret echoed in responses | pass | Details held back while a security finding in this test area is reported privately. |
| 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 |
Effects checks
| Check | Verdict | What happened |
|---|---|---|
| annotation-honestycritical Read-only tools change nothing | pass | securenow_auth_status declared read-only and changed nothing in the observed directories during a benign call (securenow_apps_list, securenow_firewall_apps, securenow_firewall_status, securenow_firewall_test_ip, securenow_notifications_list, securenow_notifications_unread, securenow_human_actions_list, securenow_human_actions_grouped_list, securenow_alert_review_runs_list, securenow_alert_review_runs_count, securenow_alert_review_group_similar, securenow_forensics_library, securenow_forensics_conversations_list, securenow_analytics_summary, securenow_automation_rules_list, securenow_rate_limit_list, securenow_rate_limit_test, securenow_firewall_hits, securenow_protection_status, securenow_overview, securenow_challenge_list, securenow_alert_rules_list, securenow_alert_rule_promotion_requests, securenow_blocklist_list, securenow_blocklist_pending_list, securenow_blocklist_stats, securenow_allowlist_list, securenow_trusted_list, securenow_agent_context, securenow_agent_history not judged: the control call failed) |
| openworld-honesty Closed-world tools stay on the machine | pass | 37 closed-world tool(s) called; nothing connected to the loopback listener (path and git tools cannot be pointed at it, so this confirms only that nothing connected out during the call) |
| 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>.
What was not covered
- Database: Not applicable. The start command takes no database connection, so the database tests did not run. ({dsn}, {host} and the like are placeholders that Sealmark fills in with its own test database.)
- HTTP: Not applicable. The server is started over stdio; the http test area needs server.url
- Files: Not applicable. The server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Git: Not applicable. No tool is classified as taking a git repository path with medium confidence or higher
- Network: Not applicable. No tool is classified as taking a URL with medium confidence or higher
- SQLite: Not applicable. No {sqlite_path} placeholder in the server config, so the harness cannot give the server a database to grade (SQLite servers only: if the server runs on SQLite, add {sqlite_path} to its args; a DuckDB server is not graded in this release, see {duckdb_path} under Not covered)
- Malformed-input probes cover the first 25 of 125 tools
- SQL tool "securenow_alert_rule_create" detected; no engine test area ran (no {dsn} or {sqlite_path} placeholder). SQL engines such as DuckDB can read and write arbitrary files; no test area tests this
- SQL tool "securenow_alert_rule_update" detected; no engine test area ran (no {dsn} or {sqlite_path} placeholder). SQL engines such as DuckDB can read and write arbitrary files; no test area tests this
- SQL tool "securenow_alert_rule_query_update" detected; no engine test area ran (no {dsn} or {sqlite_path} placeholder). SQL engines such as DuckDB can read and write arbitrary files; no test area tests this
- Tool "securenow_alert_review_run_keep_alive" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tool "securenow_alert_review_apply_group_decision" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tool "securenow_human_action_block" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tool "securenow_human_action_decision_report_add" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tool "securenow_human_action_false_positive" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tool "securenow_human_case_decision_report_add" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tool "securenow_alert_rule_condition_candidate_test" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tool "securenow_alert_rule_condition_diff" (path) was not probed by the fs test area: the server config has no {sandbox} placeholder, so the harness cannot tell which directory the server is allowed to use (a server with a wider root would read the canary legitimately); pass {sandbox} as its directory argument, or, if the server has no root argument and works in its working directory, set server.rootless: true
- Tools that a server lists only for clients that declare roots, sampling or elicitation capabilities are not seen: the harness declares none
- Tool "securenow_auth_status" is covered by the protocol checks only: the tool takes no parameters
- Tool "securenow_apps_list" is covered by the protocol checks only: the tool takes no parameters
- Tool "securenow_apps_create" is covered by the protocol checks only: argument "name" could be a path, but nothing in the tool name, its title or the parameter's own description says so; add it under tools: to include it
- Tool "securenow_apps_info" is covered by the protocol checks only: free-text parameter "key": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "securenow_firewall_apps" is covered by the protocol checks only: the tool takes no parameters
- Tool "securenow_firewall_status" is covered by the protocol checks only: free-text parameter "appKey": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "securenow_firewall_enable" is covered by the protocol checks only: free-text parameter "appKey": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "securenow_firewall_disable" is covered by the protocol checks only: free-text parameter "appKey": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "securenow_firewall_set_threshold" is covered by the protocol checks only: free-text parameter "appKey": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "securenow_traces_list" is covered by the protocol checks only: free-text parameter "environment": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "securenow_traces_show" is covered by the protocol checks only: free-text parameter "traceId": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "securenow_logs_list" is covered by the protocol checks only: free-text parameter "environment": no path, URL, command, SQL or repository signal; add it under tools: to include it
- 94 more tool(s) are covered by the protocol checks only (see the classification)
- Tool "securenow_alert_review_run_resolve" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_review_run_dismiss" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_review_run_keep_alive" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_review_run_apply_group_decision" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_review_apply_group_decision" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_review_group_similar" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_human_action_report" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_human_action_block" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_human_action_decision_report_add" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_human_action_close_no_write" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_human_action_false_positive" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_human_case_action_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_human_case_decision_report_add" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_ip_lookup" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_ip_traces" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_query" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_query_status" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_library" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_chat" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_chat_status" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_chat_confirm" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_conversations_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_forensics_conversation_get" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_analytics_summary" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_rules_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_defaults_ensure" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_rule_get" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_rule_create" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_rule_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_rule_dry_run" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_rule_execute" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_automation_rule_delete" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_get" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_test" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_remove" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_create" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_firewall_hits" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_protection_status" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_overview" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_attacker" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_protection_enable" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_protection_monitor" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_quality" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_protection_learn" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_protection_disable" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_challenge_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_challenge_create" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_challenge_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_challenge_remove" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_parse" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_rate_limit_create_from_text" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_draft" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_draft_status" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_create" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rules_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_get" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_versions" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_version_get" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_rollback" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_query_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_instant_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_conditions_get" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_condition_update" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_condition_candidate_test" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_condition_diff" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_test" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_candidate_test" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_test_result" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_runs" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_run_now" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_explain" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_request_promotion" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_promotion_requests" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_exclusions_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_exclusion_add" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_alert_rule_exclusion_remove" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_pending_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_pending_approve" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_pending_reject" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_pending_bulk_approve" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_pending_bulk_reject" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_add" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_remove" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_unblock" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_blocklist_stats" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_allowlist_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_allowlist_add" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_allowlist_remove" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_trusted_list" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_trusted_add" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_trusted_remove" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_agent_context" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_agent_verify_ip" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_agent_block_ip" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_agent_remember" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "securenow_agent_history" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- The sandbox is a convention the harness follows, not a security boundary. A malicious server runs with your user's privileges, sees the real file system and network, and can ignore cwd, HOME and PATH. Run untrusted servers in a throwaway VM or container.
- Prompt injection carried in tool output (only tool metadata is scanned)
- Authentication and transport security
- Audit logging (not measured by these test areas; only the db test area has an advisory audit check)
Grade over time
Since the run on
Same as that run: the same grade in every test area, the same server version (8.28.0), the same Sealmark version (1.0.1).
- –did not run
- Bv8.12.4Sealmark 1.0.1
- Dv8.26.0Sealmark 1.0.1
- Dv8.28.0Sealmark 1.0.1
- Dv8.28.0Sealmark 1.0.1
Badge for the README
The badge shows this automated result for version 8.28.0. It is a link to this page, not a certificate, and it changes when the next re-test does.
[](https://sealmark.dev/results/securenow/)
Files: badge SVG, card SVG, shields endpoint JSON.
Package facts
- License
- ISC
From npm, checked 22 Nov 2026. Plain facts about the package; they play no part in the grade.
Run it yourself
The command for this run is withheld while a security finding is reported privately. It is published with the report, when the finding is fixed or 90 days after the report.
Grade alerts
One email when the grade of securenow changes after a re-test. Nothing else, and every email has a link to stop them.
Each of 613 verdicts was checked independently, and Sealmark was wrong on some: how reliable Sealmark is.
Is this wrong?
Reply to our private report 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.