AI Agent Skill HUB

safe-file-reader

Read files from documents directory safely

7 stars
byDemerzels-lab
View on GitHubInstallation ↓

Best use case

safe-file-reader is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Read files from documents directory safely

Teams using safe-file-reader should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/path-traversal-reader/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/dgriffin831/skill-scan/test-fixtures/path-traversal-reader/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/path-traversal-reader/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How safe-file-reader Compares

Feature / Agentsafe-file-readerStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Read files from documents directory safely

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Safe File Reader

Reads files from the documents directory with validation.

## Usage

Provide filename to read.

Related Skills

openclaw-safety-coach

7
from Demerzels-lab/elsamultiskillagent

Safety coach for OpenClaw users. Refuses harmful, illegal, or unsafe requests and provides practical guidance to reduce ecosystem risk (malicious skills, tool abuse, secret exfiltration, prompt injection).

Send Me My Files - R2 upload with short lived signed urls

7
from Demerzels-lab/elsamultiskillagent

Upload files to Cloudflare R2, AWS S3, or any S3-compatible storage.

book-reader

7
from Demerzels-lab/elsamultiskillagent

Read books (epub, pdf, txt) from various sources with progress tracking.

feishui-file-sender

7
from Demerzels-lab/elsamultiskillagent

Send files via Feishu channel using message tool with filePath parameter.

safe-exec

7
from Demerzels-lab/elsamultiskillagent

Protect against prompt injection from shell command output. Wrap untrusted commands (curl, API calls, reading user-generated files) with UUID-based security boundaries. Use when executing commands that return external/untrusted data that could contain prompt injection attacks.

filewave

7
from Demerzels-lab/elsamultiskillagent

Query and manage FileWave UEM device inventory via REST API.

camino-safety-checker

7
from Demerzels-lab/elsamultiskillagent

Find 24-hour businesses, well-lit public areas, transit stations, police stations, and hospitals near any location.

iyeque-pdf-reader

7
from Demerzels-lab/elsamultiskillagent

Extract text, search inside PDFs, and produce summaries.

file-repair-skill

7
from Demerzels-lab/elsamultiskillagent

You are the `file-repair` skill.

twitter-reader

7
from Demerzels-lab/elsamultiskillagent

A comprehensive skill for reading and extracting data from X (formerly Twitter) tweets using multiple reliable data.

perplexity-safe

7
from Demerzels-lab/elsamultiskillagent

Use Perplexity API for web-grounded AI search.

safe-update

7
from Demerzels-lab/elsamultiskillagent

Update OpenClaw from source code.