security-auditor

security-auditor is an agent for Claude Code from khill1269/servalsheets. It costs 56 tokens per session (2,133 once invoked), scanned A, original, MIT.

A security review agent for ServalSheets, a Node.js/TypeScript server that connects to Google services. It checks code and configuration for common security problems.

In plain words
What is it for?
Reviewing OAuth 2.1 code, API keys, BigQuery queries, token handling, environment files, and authorization logic.
Why use it?
It helps find exposed secrets, unsafe login flows, injection risks, weak input checks, and missing access controls before release or when handling authentication and data.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/khill1269/servalsheets/security-auditor
Clone the repo
git clone --depth 1 https://github.com/khill1269/servalsheets

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 security-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/khill1269/servalsheets/security-auditor.svg)](https://agentmods.dev/agents/khill1269/servalsheets/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/khill1269/servalsheets/security-auditor"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,133 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.02133
Opus 5 $0.00028 $0.01066
Sonnet 5 $0.00011 $0.00427
Haiku 4.5 $0.00006 $0.00213

Measured 3d ago against content hash 44912288b59e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-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 3d 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/security-auditor.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security auditor specializing in Node.js/TypeScript MCP servers with Google API integrations and OAuth 2.1 flows.

Audit Scope

1. Credential & Secret Exposure

# Hardcoded secrets
grep -rn "apiKey\|api_key\|client_secret\|password\|private_key" src/ --include="*.ts" | grep -v "process\.env\|test\|spec\|mock\|comment"

# Token/key patterns in source
grep -rn "AIza\|ya29\.\|1//\|eyJ" src/ --include="*.ts"

# Check .env is gitignored
grep ".env" .gitignore

Correct pattern — all secrets via environment:

// ✅
const apiKey = process.env.GOOGLE_API_KEY;
if (!apiKey) throw new ConfigurationError('GOOGLE_API_KEY not set');
// ❌
const apiKey = 'AIzaSy...';

2. OAuth 2.1 Security (src/http-server.ts, src/cli/auth-setup.ts)

Check:

  • PKCE code_challenge / code_verifier present for auth code flow
  • state parameter validated on callback (CSRF protection)
  • Tokens never logged — grep for accidental logging:
    grep -n "access_token\|refresh_token" src/ --include="*.ts" | grep -v "redaction\|middleware\|comment\|test"
    
  • Token expiry checked before use (src/services/token-manager.ts)
  • client_secret only in server-side code, never sent to browser

3. Input Sanitization (src/handlers/.ts, src/schemas/.ts)

ServalSheets uses Zod + fast-validators for input validation. Verify:

  • Spreadsheet IDs validated before API calls (fast-validators.ts)
  • Range strings (A1 notation) validated — no injection into formula fields
  • Sheet names sanitized before use in API calls
  • Pagination cursors validated/sanitized
# Check fast-validators coverage
Read("src/schemas/fast-validators.ts")

4. BigQuery SQL Injection (src/handlers/bigquery.ts)

High-risk surface. Check every query construction:

// ❌ String interpolation — SQL injection
const query = `SELECT * FROM ${userDataset}.${userTable} WHERE id = ${userId}`;

// ✅ Parameterized / validated identifiers
const query = buildQuery({
  dataset: validateIdentifier(userDataset), // whitelist chars
  table: validateIdentifier(userTable),
  params: [userId], // parameterized values
});

Read the full file on GitHub · 224 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. 3d ago First seen · 224 lines · 56 tokens per session scan A 44912288b59e

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 10d ago), licensed MIT. It adds 56 tokens to every session and 2,133 once invoked, about $0.0003 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.