audit-logs

audit-logs is a skill for Claude Code from ShipBook/shipbook-mcp. It costs 45 tokens per session (1,163 once invoked), scanned A, original, MIT.

A read-only codebase review that checks logging statements for personal information, secrets, and other sensitive data. Logs are records that software writes to help diagnose what happened.

In plain words
What is it for?
Use it to scan application logs for exposed passwords, tokens, payment-card numbers, identity numbers, and other privacy or security problems, then review the findings before fixing them.
Why use it?
It reveals data that should not be written to logs without changing the code automatically.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the shipbook plugin — 5 skills, 1 MCP server shipped together

Good fit Use it to scan application logs for exposed passwords, tokens, payment-card numbers, identity numbers, and other privacy or security problems, then review the findings before fixing them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shipbook/shipbook-mcp/audit-logs
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 ShipBook/shipbook-mcp --skill audit-logs
Clone the repo
git clone --depth 1 https://github.com/ShipBook/shipbook-mcp

Made for: Claude Code.

Or install shipbook, the plugin that ships this one along with the rest of its 5 skills, 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.

agentmods badge for audit-logs

README.md
[![agentmods](https://agentmods.dev/badge/skills/shipbook/shipbook-mcp/audit-logs/github.svg)](https://agentmods.dev/skills/shipbook/shipbook-mcp/audit-logs)
Your own site
<a href="https://agentmods.dev/skills/shipbook/shipbook-mcp/audit-logs"><img src="https://agentmods.dev/badge/skills/shipbook/shipbook-mcp/audit-logs/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.

agentmods 80×15 button for audit-logs

Your own site · 80×15
<a href="https://agentmods.dev/skills/shipbook/shipbook-mcp/audit-logs"><img src="https://agentmods.dev/badge/skills/shipbook/shipbook-mcp/audit-logs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,163 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01163
Opus 5 $0.00023 $0.00581
Sonnet 5 $0.00009 $0.00233
Haiku 4.5 $0.00005 $0.00116

Measured 9d ago against content hash 10022419e3a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-logs 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 9d 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/audit-logs/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Logs

Scan the codebase for logging issues — PII exposure, secrets, and sensitive data leaks.

Important: This skill is read-only. It reports findings but does NOT make changes automatically. Always present the report first and ask the user what they want to fix.

Steps

1. Find all log statements

Scan the project for all logging calls. Look for:

  • Shipbook: log.e(), log.w(), log.i(), log.d(), log.v(), Log.e(), Log.w(), etc.
  • Standard: console.log, console.error, console.warn, print(), NSLog(), android.util.Log
  • Framework loggers: logger.info(), logger.error(), Timber.d(), etc.

2. Check for secrets and sensitive data (high priority)

These must never appear in logs. Flag immediately:

  • Passwords and secrets — variable names like password, secret, token, apiKey, accessToken, refreshToken, authorization
  • Full credit card numbers — patterns like \d{4}[-\s]?\d{4}[-\s]?\d{4}[-\s]?\d{4}. Logging the last 4 digits is acceptable (e.g., **** **** **** 1234), but the full number must never be logged.
  • SSN, national ID, and passport numbers — variable names like ssn, socialSecurity, nationalId, idNumber, passportNumber, passport. These are government-issued identifiers used for identity theft and are protected under GDPR, CCPA, and most privacy laws. They must never appear in logs.

These are non-negotiable — present them as critical findings that need immediate attention.

3. Check for personal identifiers (ask user)

These are suggestions — the user may have valid reasons to log them. Present as recommendations and ask before changing:

  • Email addresses logged directly — suggest using userId or hashed identifier instead
  • Phone numbers — variable names like phone, phoneNumber, mobile
  • Physical addresses — address, street, zipCode, postalCode
  • Full names — fullName, firstName, lastName logged directly in message strings

Recommendation example:

// Consider replacing direct PII with internal identifiers:
log.i(`User logged in: ${user.email}`)
// Could be:
log.i(`User logged in: ${user.id}`)

Read the full file on GitHub · 91 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.

  1. 9d ago First seen · 91 lines · 45 tokens per session scan A 10022419e3a7

Subscribe to this mod's changes

audit-logs is a skill published in the GitHub repository ShipBook/shipbook-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,163 once invoked, about $0.0002 per session on Opus 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 2026-08-31.