Pdf Extract

Extract text from PDF files for LLM processing

Security Scan

The skill's requirements and instructions are consistent with its stated purpose (extracting text from PDFs using pdftotext); nothing requests unrelated credentials or dangerous installs.

Purpose & Capability

The skill is for extracting text from PDFs and declares/installs the pdftotext binary (poppler-utils), which is exactly what's needed for that job.

Instruction Scope

SKILL.md instructs using pdftotext indirectly but shows example commands using a 'pdf-extract' wrapper that is not provided in the bundle. The instructions otherwise stay within scope (convert PDFs to text) and do not ask for unrelated files or secrets.

Install Mechanism

Install spec uses dnf to install poppler-utils (pdftotext). This is a standard distro package install and low-risk. No downloads from arbitrary URLs or archive extraction are used.

Credentials

No environment variables, credentials, or config paths are requested — appropriate and minimal for the stated purpose.

Persistence & Privilege

The skill does not request persistent presence (always: false) and does not attempt to modify other skills or system-wide settings.

Assessment

This instruction-only skill is coherent: it needs the pdftotext tool (poppler-utils) to work and nothing else. Before installing, confirm you are on a dnf-based system or install pdftotext by another supported method. Note the SKILL.md examples reference a 'pdf-extract' wrapper command that is not included — the agent will need to call pdftotext directly or you should ask the skill author for the wrapper. No credentials or unusual system access are requested, but installing packages requires sudo/root on the host, so ensure you trust the source of the package repository and have appropriate privileges.

Extract text from PDF files for LLM processing. Uses pdftotext from the poppler-utils package to convert PDF documents into plain text.

Commands

# Extract all text from a PDF
pdf-extract "document.pdf"

# Extract text from specific pages
pdf-extract "document.pdf" --pages 1-5

Install

sudo dnf install poppler-utils