Skip to main content
skill CX Codex

protect-with-password — Claude Code skill: what it does

protect-with-password — a skill for Claude Code produces a secure password and locks specified files using AES-256. Triggers when encrypting deliverable documents prior to sharing.

MIT 115 installs ★ 632 updated 2026-07-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add transilienceai/communitytools --skill protect-with-password -a claude-code
Open on GitHub

What protect-with-password does

The tool executes tools/protect_with_password.py on selected paths, writing locked outputs either next to inputs or inside --out-dir. Original files remain completely untouched throughout execution. A 24-character key is minted automatically, though --password allows passing an existing string.

Documents ending in .pdf receive native AES-256 protection via qpdf with a pypdf fallback, producing <name>-protected.pdf. Spreadsheets, presentations, text documents, and other extensions are placed into <name>.7z containers with encrypted file headers through 7-Zip -mhe=on. Processing halts with an exit code of 1 instead of downgrading to obsolete schemes like ZipCrypto or RC4.

Keys are logged to PROTECT-PASSWORD.txt with mode 600, surfaced in stderr, and returned within JSON output. Running this script requires Python 3 along with underlying command-line encryption binaries.

What it helps with

  • lock PDF deliverables using native AES-256 protection
  • wrap Office spreadsheets and slides into password-protected 7z archives
  • mint a 24-character encryption key across multiple files
  • generate protected copies without modifying source deliverables

Example prompts for the agent

  • Password-protect summary.pdf and data.xlsx before sending
  • Lock all deliverables in output/ using a single generated password
  • Encrypt deck.pptx with AES-256 using protect-with-password

How to install protect-with-password

1Skills CLI (Vercel)

npx skills add transilienceai/communitytools --skill protect-with-password -a claude-code

2Manually: put the files in place

~/.claude/skills/protect-with-password/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/protect-with-password/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about protect-with-password

How to install protect-with-password in Claude Code?

Run npx skills add transilienceai/communitytools --skill protect-with-password -a claude-code.

What does protect-with-password do?

It creates AES-256 encrypted duplicates of referenced files using a single generated password, outputting protected PDFs or encrypted .7z archives.

What is required to run protect-with-password?

Environment needs Python 3, qpdf or pypdf for PDF handling, and 7-Zip for archiving other file formats.

Source text

SKILL.md · MIT
---
name: protect-with-password
description: Generate ONE strong password and apply it to each referenced file (PDF, Word, Excel, PowerPoint, or any type). Use when asked to password-protect / encrypt / lock one or more deliverable files with a single password before sharing.
---

# Protect With Password

Mint a single strong password and password-protect every referenced file with it, "accordingly" per file type. Deterministic, non-destructive (originals are never touched), AES-256 or nothing.

## Run it

```
python3 tools/protect_with_password.py FILE [FILE ...] \
    [--password PW] [--length 24] [--out-dir DIR] \
    [--password-file PATH | --no-password-file]
```

- Pass every file the user referenced as positional arguments.
- By default a strong password is generated (`--password` overrides to reuse one).
- Protected copies are written alongside each input, or into `--out-dir`.
- The tool prints a JSON summary on stdout and a password banner on stderr, and (unless `--no-password-file`) writes the password to a chmod-600 `PROTECT-PASSWORD.txt`.

## How each type is protected

| File | Protection | Result |
|------|-----------|--------|
| `.pdf` | Native AES-256 (qpdf → pypdf fallback) | `<name>-protected.pdf` — recipient is prompted for the password on open |
| `.docx/.xlsx/.pptx`, `.doc/.xls/.ppt`, images, anything else | AES-256 7-Zip archive (`-mhe=on`, filenames encrypted) | `<name>.7z` — recipient extracts with the password (7-Zip / Keka / WinRAR) |

Native in-file Office (MS-OFFCRYPTO "agile") encryption needs LibreOffice or a dedicated encryptor that is not bundled here, so Office files are wrapped in a strong AES-256 archive instead. If no AES-256 tool is available for a file, it is reported as a failure — never downgraded to weak ZipCrypto/RC4 (no false assurance).

## After running

Relay the password to the user and remind them to **share it OUT-OF-BAND** — never in the same channel/email as the protected files — and to delete `PROTECT-PASSWORD.txt` once handed over. Exit code is 0 only if every file was protected; 1 if any failed (check `results[].reason`).

Related: [`tools/protect_deliverable.py`](../../tools/protect_deliverable.py) does the engagement-wide variant (one protected PDF + an AES-256 deliverable zip); this skill protects an arbitrary set of individual files.

© transilienceai · MIT · transilienceai/communitytools

Similar skills

All skills for Security →

From the same set42

The whole set →
pentest-engagement pentest-engagement runs scoped penetration tests on web applications or networks, verifies findings immediately, and produces a structured PDF report. CX Codex +1 157installs regression-sweep regression-sweep is a Claude Code skill that rechecks confirmed vulnerabilities weekly for patches, mitigations, and re-introductions. It runs on Mondays or manually after major deployments. CX Codex +1 149installs ti-ingest ti-ingest parses threat-intel payloads with CVEs and affected assets into queue files for validation agents. CX Codex +1 147installs pci-secure-software Checks an app against PCI Secure Software Standard v2.0 and returns a status for every Test Requirement, tied to a cited line of code or docs. CX Codex +1 141installs cloud-defense cloud-defense maps post-compromise cloud attack stages to log signals and preventive controls. Use it for AWS, Azure, and GCP detection work or posture reviews. CX Codex +1 133installs transilience-report-style transilience-report-style is a Claude Code skill that defines styling for Threat Intelligence reports generated as A4 PDFs with ReportLab. Light theme is the default. CX Codex +1 133installs authenticated-session-acquisition The authenticated-session-acquisition skill obtains a legitimate MFA/OTP session and saves reusable artifacts for browser and post-auth API testing. CX Codex +1 126installs network-appliance-offensive network-appliance-offensive — a skill for active security testing of firewalls, VPN endpoints, and network appliances. CX Codex +1 120installs

Project sponsors

Companies that keep this analytics open