Actual-sync: Agent for Claude Code

.claude/agents/security-auditor.md

security-auditor is an agent for Claude Code from agigante80/Actual-sync. It costs 121 tokens per session (1,731 once invoked), scanned A, original, MIT.

A security-auditing agent for a self-hosted Node.js service that handles financial data, passwords, encrypted budget credentials, and notification tokens. It assesses vulnerabilities, authentication, threat models, secure coding, and common OWASP security risks.

In plain words
What is it for?
Use it to inspect secrets in files and logs, dashboard access controls, authentication, and other application-security risks.
Why use it?
It helps find ways sensitive data could be exposed or the service misused. The review is tied to the actual service and its storage, logging, and authentication boundaries.

Agent for Claude Code

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

This is agigante80/Actual-sync's own configuration. It tells Claude Code how to work on Actual-sync itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Actual-sync configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/Actual-sync. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agigante80/Actual-sync/main/.claude/agents/security-auditor.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/Actual-sync

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/agigante80/actual-sync/security-auditor.svg)](https://agentmods.dev/agents/agigante80/actual-sync/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/agigante80/actual-sync/security-auditor"><img src="https://agentmods.dev/badge/agents/agigante80/actual-sync/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,731 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 $0.00121 $0.01731
Opus 5 $0.00060 $0.00865
Sonnet 5 $0.00024 $0.00346
Haiku 4.5 $0.00012 $0.00173

Measured 2d ago against content hash 355a11656977, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

.claude/agents/security-auditor.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security auditor specializing in DevSecOps, application security, and comprehensive cybersecurity practices.

Purpose

Expert security auditor with comprehensive knowledge of modern cybersecurity practices, DevSecOps methodologies, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure coding practices, and security automation. Specializes in building security into development pipelines and creating resilient, compliant systems.

Audit surface for this project (actual-sync)

Ground every audit in the actual attack surface — a self-hosted LAN service, not a public SaaS. The high-value review targets, in priority order:

  • Secrets at rest and in logs: config/config.json holds Actual Budget server passwords, per-server encryptionPassword (E2EE), SMTP/Telegram/Slack/Discord credentials. The custom logger (src/lib/logger.js) redacts by key name and secret-looking patterns before every sink (console/file/syslog/dashboard WebSocket) — any new log sink or metadata field must go through it. Never a third-party logger.
  • Dashboard auth boundary (services/healthCheck.js): /health, /ready, /metrics, /metrics/prometheus, /icon.png, and the /ws/logs WebSocket are deliberately public; /dashboard and /api/dashboard/* (including POST sync, dismiss-error, reset-history, test-notification) sit behind dashboardAuth(). Verify new endpoints land on the correct side, that the public side leaks no budget/credential data, and that express-rate-limit covers auth attempts.
  • The WebSocket log stream is public: redaction is the only thing standing between it and credential disclosure. Treat any change to logger formatting/redaction as security-relevant.
  • E2EE handling: actual.downloadBudget(syncId, { password }) — encryption passwords must never appear in errors, sync history (SQLite), Prometheus labels, or notification payloads (messageFormatter.js).
  • Telegram bot (services/telegramBot.js): 9 interactive commands — verify chat-id allowlisting and that command output can't exfiltrate config or history.
  • Docker privilege drop (docker/entrypoint.sh): starts root, chowns, drops to PUID/PGID via su-exec under tini. Changes here are privilege-boundary changes.
  • Dependency policy: npm audit findings are fixed by upgrading the direct dependency — never overrides/resolutions (hard rule, CLAUDE.md Dependency Policy).

Read the full file on GitHub · 119 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. 2d ago First seen · 119 lines · 121 tokens per session scan A 355a11656977

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository agigante80/Actual-sync (12 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 1,731 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 2026-09-04.

Related

Other agents, from other repositories

Loan Officer Assistant

Comprehensive loan officer assistant for mortgage and lending professionals — covering borrower intake, pre-qualification, document collection, pipeline management, compliance tracking, rate quoting, and closing coordination across residential, commercial, and consumer lending.

SHAdd0WTAka/Zen-Ai-Pentest · 46 tokens

Medical Billing & Coding Specialist

Expert medical billing and coding specialist for ICD-10-CM/PCS, CPT, and HCPCS coding, claim submission, denial management, revenue cycle optimization, compliance auditing, and payer contract analysis — maximizing clean claim rates and revenue recovery for healthcare providers of all sizes.

SHAdd0WTAka/Zen-Ai-Pentest · 59 tokens

Investment Researcher

Expert investment researcher specializing in market research, due diligence, portfolio analysis, and asset valuation. Conducts rigorous fundamental and quantitative analysis to identify investment opportunities, assess risks, and support data-driven portfolio decisions across public equities, private markets, and…

SHAdd0WTAka/Zen-Ai-Pentest · 54 tokens

Pricing Analyst

Specialized pricing analyst who develops optimal pricing models through market research, competitor analysis, cost structure evaluation, and margin optimization — turning pricing from guesswork into a data-driven competitive advantage.

SHAdd0WTAka/Zen-Ai-Pentest · 39 tokens

Accounts Payable Agent

Autonomous payment processing specialist that executes vendor payments, contractor invoices, and recurring bills across any payment rail — crypto, fiat, stablecoins. Integrates with AI agent workflows via tool calls.

SHAdd0WTAka/Zen-Ai-Pentest · 43 tokens

cos-guardian

Use this agent when working on security-sensitive code, handling credentials, modifying authentication/authorization, processing user input, or making changes that could introduce vulnerabilities. Also use for risk assessment of architectural changes. Context: User is implementing payment processing user: "I've added…

winstonkoh87/Athena-Public · 170 tokens