The Agent Skills Directory

[SAFE]: The skill provides legitimate PDF manipulation functionality using established libraries like pypdf, pdfplumber, and reportlab. All scripts and documentation are consistent with the skill's stated purpose.
[COMMAND_EXECUTION]: The skill documentation and scripts utilize standard PDF-related command-line utilities (qpdf, pdftotext, pdftk, magick) for document processing. These tools are used for their intended purposes without signs of malicious intent or unauthorized access.
[EXTERNAL_DOWNLOADS]: The skill references the installation and use of well-known, trusted libraries (e.g., pytesseract, pdf2image, pdf-lib) from official package registries.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it processes untrusted PDF content. It utilizes established parsing libraries for extraction but does not define explicit boundary markers for the extracted text before it enters the agent's context. This is a characteristic of document processing tools and is documented here as a standard risk factor.

pdf