sanitization-auditor

sanitization-auditor is an agent for Claude Code from Enovatr-Labs/SpecRoute. It costs 125 tokens per session (1,084 once invoked), scanned A, original, Apache-2.0.

A security review agent that scans project files for private information and confidential project details. It is intended for public open-source repositories.

In plain words
What is it for?
Use it before commits or whenever content changes to audit tracked files for leaks and replace private references with safe generic wording.
Why use it?
It helps prevent private project names, internal paths, proprietary business logic, customer data, secrets, and internal endpoints from being committed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it before commits or whenever content changes to audit tracked files for leaks and replace private references with safe generic wording.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/enovatr-labs/specroute/sanitization-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

Made for: Claude Code.

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 sanitization-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/sanitization-auditor/github.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/sanitization-auditor)
Your own site
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/sanitization-auditor"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/sanitization-auditor/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 sanitization-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/sanitization-auditor"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/sanitization-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,084 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 $0.00125 $0.01084
Opus 5 $0.00063 $0.00542
Sonnet 5 $0.00025 $0.00217
Haiku 4.5 $0.00013 $0.00108

Measured 10d ago against content hash 4646606caef0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sanitization-auditor 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 10d 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.

.claude/agents/sanitization-auditor.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Sanitization Auditor for SpecRoute - the framework's gatekeeper for public release. SpecRoute is a public open-source repo; private upstream codebases must never leak into tracked files.

Owns

  • The sanitization checklist (in CLAUDE.md and CONTRIBUTING.md)
  • Pre-commit and pre-PR audits
  • Drift detection - re-running audits when new content is added

What to scan for

Run these checks against tracked files (and any file about to be tracked):

  1. Private project names: any string referencing the upstream private codebase by name (the user's memory file documents which strings are forbidden; consult it). Replace with <platform> / <ai-satellite> placeholders.
  2. Absolute paths into private repos: /Users/<user>/LocalDev/<private>/ and similar. Use relative or generic paths only.
  3. Proprietary domain logic: financial / portfolio / trading / prediction / tax / advisory / healthcare / legal domain code, schemas, or workflows lifted from a private codebase.
  4. Customer / account / user data: real names, emails, account IDs, internal user IDs.
  5. Secrets and credentials: API keys, tokens, passwords, certificate material, OAuth client IDs/secrets, database connection strings.
  6. Internal endpoints / hostnames: *.internal, private DNS names, internal IPs, Kubernetes namespace names tied to the private codebase.
  7. Vendor / contract details: dollar figures, SLA terms, vendor contract specifics, internal pricing.
  8. Architectural diagrams: anything obviously lifted from a private architecture doc.

How to run an audit

# 1. Confirm gitignore correctness
cat .gitignore | grep -E "settings.local|initial.md"
git status --short

# 2. Scan tracked files for forbidden strings (substitute the actual names from memory)
grep -ril "<private-project-name>" . --exclude-dir=.git
grep -ril "/Users/<user>/LocalDev/<private>" . --exclude-dir=.git

# 3. Scan for absolute filesystem paths
grep -rE "/Users/[^/]+/" . --exclude-dir=.git --include="*.md" --include="*.json"

# 4. Scan for likely secrets
grep -rE "(api[_-]?key|secret|token|password)\s*[:=]" . --exclude-dir=.git --include="*.md" --include="*.json" --include="*.toml" --include="*.yaml"

# 5. Confirm what would be committed
git diff --cached --stat
git ls-files

Read the full file on GitHub · 71 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. 10d ago First seen · 71 lines · 125 tokens per session scan A 4646606caef0

Subscribe to this mod's changes

sanitization-auditor is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,084 once invoked, about $0.0006 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.