sensitive-data-protection

sensitive-data-protection is a skill for Claude Code from latestaiagents/agent-skills. It costs 78 tokens per session (2,512 once invoked), scanned A, original, MIT.

A guide to protecting sensitive information such as passwords, payment cards, API keys, and personal data. It covers encryption, masking, safe storage, and safe transmission.

In plain words
What is it for?
Use it when handling personal data, credentials, payment information, encryption, HTTPS, or privacy and compliance requirements.
Why use it?
It helps prevent secrets and personal or financial information from appearing in logs, URLs, errors, or unprotected storage and connections.

Skill for Claude Code

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

Part of the owasp-guardian plugin — 6 skills shipped together , and of security, latestaiagents

Good fit Use it when handling personal data, credentials, payment information, encryption, HTTPS, or privacy and compliance requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/sensitive-data-protection
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 latestaiagents/agent-skills --skill sensitive-data-protection
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install owasp-guardian, the plugin that ships this one along with the rest of its 6 skills.

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 sensitive-data-protection

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/sensitive-data-protection.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/sensitive-data-protection)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/sensitive-data-protection"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/sensitive-data-protection.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,512 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 $0.00078 $0.02512
Opus 5 $0.00039 $0.01256
Sonnet 5 $0.00016 $0.00502
Haiku 4.5 $0.00008 $0.00251

Measured 4d ago against content hash a5356d3efb0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sensitive-data-protection 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 4d 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/security/owasp-guardian/sensitive-data-protection/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sensitive Data Protection (OWASP A03)

Protect sensitive data in transit and at rest through proper encryption, masking, and access controls.

When to Use

  • Handling user personal information (PII)
  • Storing or transmitting passwords
  • Processing payment card data
  • Managing API keys and secrets
  • Implementing data encryption
  • Ensuring compliance (GDPR, PCI-DSS, HIPAA)

Sensitive Data Categories

Category Examples Protection Level
Credentials Passwords, API keys, tokens CRITICAL
Financial Credit cards, bank accounts CRITICAL
Personal (PII) SSN, passport, driver's license HIGH
Health (PHI) Medical records, prescriptions HIGH
Contact Email, phone, address MEDIUM
Behavioral Browsing history, preferences MEDIUM

Detection Patterns

Exposed Sensitive Data

// VULNERABLE - Logging sensitive data
console.log('User login:', { email, password });
logger.info(`Payment processed: ${creditCardNumber}`);

// VULNERABLE - Sensitive data in URL
res.redirect(`/reset?token=${token}&email=${email}`);

// VULNERABLE - Sensitive data in error messages
throw new Error(`Invalid password for user ${email}`);

// VULNERABLE - Storing unencrypted
user.ssn = req.body.ssn;
user.creditCard = req.body.cardNumber;

Weak Encryption

// VULNERABLE - Weak algorithms
const encrypted = crypto.createCipher('des', key); // DES is broken
const hash = crypto.createHash('md5').update(data); // MD5 is broken

// VULNERABLE - ECB mode
crypto.createCipheriv('aes-256-ecb', key, ''); // ECB leaks patterns

// VULNERABLE - Hardcoded keys
const ENCRYPTION_KEY = 'my-secret-key-123';

// VULNERABLE - Predictable IV
const iv = Buffer.alloc(16, 0); // All zeros IV

Secure Implementation

1. Encryption at Rest

const crypto = require('crypto');

const ALGORITHM = 'aes-256-gcm';
const KEY = Buffer.from(process.env.ENCRYPTION_KEY, 'hex'); // 256-bit key

function encrypt(plaintext) {
  const iv = crypto.randomBytes(16);
  const cipher = crypto.createCipheriv(ALGORITHM, KEY, iv);

  let encrypted = cipher.update(plaintext, 'utf8', 'hex');
  encrypted += cipher.final('hex');

  const authTag = cipher.getAuthTag();

  // Return IV + AuthTag + Ciphertext
  return iv.toString('hex') + ':' + authTag.toString('hex') + ':' + encrypted;
}

function decrypt(encryptedData) {
  const [ivHex, authTagHex, ciphertext] = encryptedData.split(':');

  const iv = Buffer.from(ivHex, 'hex');
  const authTag = Buffer.from(authTagHex, 'hex');

  const decipher = crypto.createDecipheriv(ALGORITHM, KEY, iv);
  decipher.setAuthTag(authTag);

  let decrypted = decipher.update(ciphertext, 'hex', 'utf8');
  decrypted += decipher.final('utf8');

  return decrypted;
}

// Usage
user.encryptedSSN = encrypt(ssn);
const ssn = decrypt(user.encryptedSSN);

Read the full file on GitHub · 377 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. 4d ago First seen · 377 lines · 78 tokens per session scan A a5356d3efb0e

Subscribe to this mod's changes

sensitive-data-protection is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 2,512 once invoked, about $0.0004 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 2026-09-03.