pdf-manipulation

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several standard command-line utilities including pdftk, qpdf, ghostscript, and poppler-utils to perform document operations. This matches the stated purpose of the skill.
  • [EXTERNAL_DOWNLOADS]: The documentation includes standard installation commands for system-level dependencies using apt-get and Homebrew. It also references well-known packages from official registries, specifically pdf-lib and pdf-parse for Node.js, and PyPDF2 and pypdf for Python.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process data from external PDF files.
  • Ingestion points: The skill reads untrusted data from PDF files during text extraction, metadata retrieval, and manipulation workflows (e.g., pdftotext, pdfinfo, PDFDocument.load).
  • Boundary markers: Absent. The provided agent prompt does not specify delimiters or include instructions for the agent to ignore potentially malicious commands embedded within the PDF content.
  • Capability inventory: The skill possesses significant capabilities including file system read/write access and the execution of multiple subprocesses for PDF processing.
  • Sanitization: Absent. There are no mechanisms described to sanitize or validate extracted text or metadata before it is presented to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:36 AM