A read-only ServiceNow security review that checks access rules, hardening settings, cross-scope access, and why a particular user can or cannot perform an operation.

Use it for security reviews, hardening checks, and questions about whether a user can read, write, create, or delete ServiceNow data.

It helps explain exposed or blocked access without changing roles, permissions, or settings. Any changes must be handled through a separate write process.

sn-security — Skill for Claude Code by IvanBBaev/servicenow-mcp-ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add IvanBBaev/servicenow-mcp-ai --skill sn-security

Clone the repo

git clone --depth 1 https://github.com/IvanBBaev/servicenow-mcp-ai

Made for: Claude Code.

Or install servicenow-mcp-ai, the plugin that ships this one along with the rest of its 8 skills, 2 agents, 3 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ivanbbaev/servicenow-mcp-ai/sn-security/github.svg)](https://agentmods.dev/skills/ivanbbaev/servicenow-mcp-ai/sn-security)

Your own site

<a href="https://agentmods.dev/skills/ivanbbaev/servicenow-mcp-ai/sn-security"><img src="https://agentmods.dev/badge/skills/ivanbbaev/servicenow-mcp-ai/sn-security/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ivanbbaev/servicenow-mcp-ai/sn-security"><img src="https://agentmods.dev/badge/skills/ivanbbaev/servicenow-mcp-ai/sn-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 826 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00073	$0.00826
Opus 5.5	$0.00029	$0.00330
Sonnet 5.5	$0.00015	$0.00165
Haiku 4.5	$0.00007	$0.00083

Measured 2d ago against content hash de18adf0b8cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sn-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/sn-security/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sn-security — who can do what, and what is exposed

Read-only analysis through the ServiceNow MCP server. Never change a role, ACL or property from this skill.

When not to use

Granting or revoking a role, or changing an ACL — that is a write; plan it through sn-safe-write.
A failing script, rule or flow that is not about access — use sn-triage.
Comparing the security setup of two instances — use sn-drift.

Steps

Packages: this skill calls tools from codecheck, directory and docs, which the default discovery profile leaves off. Read enabledPackages in servicenow_get_status; for a missing package, enable it with the server's enable_package admin tool and tell the user, or ask the operator to add it to SN_TOOL_PACKAGES. A package listed in deniedPackages cannot be enabled — skip the steps that need it and report them as not checked. directory reads user data: say so before you enable it.
One user's access — the question names a user and a table, record or field: servicenow_explain_access with user, table and operation (read, write, create or delete); add sys_id for one record and field for a field ACL. It returns the user's roles, the row (and field) ACL chain with the rule that matched, and its role, condition and script parts. A script part is undetermined — it is not evaluated — so the decision can be undetermined too; say which ACL holds it. Use format: "markdown" for a report with a decision diagram. Then stop unless a wider review was asked for.
ACL scan and hardening: servicenow_check_code_health with no scope — read "Security — ACL scan" (open, public, scripted and elevated ACLs, public REST resources and UI pages, tables without an ACL) and "Security — hardening" (each rule against sys_properties). For a failed rule, state the property, its value, the expected value and the rationale. A rule that is not set relies on the platform default; an unreadable sys_properties means unknown, not compliant.
Full document: servicenow_document_instance with kinds: ["security"] and write: false to cross-check step 3 and list what could not be read.
One scoped app: servicenow_document_app with the scope and detail: true, then read "Cross-scope access". An outbound call with status missing or denied fails at runtime; requested needs an admin decision. Detection is static, so dynamic calls are not seen.

Read the full file on GitHub · 61 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 61 lines · 73 tokens per session scan A de18adf0b8cf

Subscribe to this mod's changes

sn-security is a skill published in the GitHub repository IvanBBaev/servicenow-mcp-ai (8 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 826 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

LLM Security ai itsm mcp model-context-protocol servicenow

inbound-email

Handle email arriving at a ServiceNow instance — inbound email action ordering and stop-processing, the real syseventinemailaction column names, and reading sysemail when a message created no record.

serac-labs/serac · 43 tokens

instance-performance-triage

Answer "the instance is slow" or "my nightly job never ran" from ServiceNow's own telemetry — transaction logs, syslog, systrigger, progress workers, execution trackers — instead of ad-hoc scripts that add to the load.

serac-labs/serac · 55 tokens

mcp-tool-discovery

Find and call tools on this ServiceNow MCP server — the two meta-tools it starts with, why a missing session id makes every other tool unreachable, which queries actually match, and which advertised tools are not on the server at all.

serac-labs/serac · 53 tokens

workspace-builder

Build ServiceNow App Engine Studio applications — sysscope creation, scoped tables, sysawworkspace with lists/forms, the sysux record chain behind UI Builder workspaces, data brokers, and application export readiness checks. Never create a UI Builder page by inserting a sysuxpage row.

serac-labs/serac · 62 tokens

background-script-execution

What actually happens when you call snowexecutescript — the Scripted REST endpoint Serac auto-deploys on first use, the scheduled-job fallback, what scheduledjobpending means, and how to get output back when the call comes home empty.

serac-labs/serac · 54 tokens

change-rollback

Undo a change already written to a ServiceNow instance — recover the prior payload from sysupdateversion, write it back without corrupting it, and know which damage update set back-out, Deleted Records, or nothing at all can reverse.

serac-labs/serac · 51 tokens