pdf-conversion-router

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection risk factor identified.
  • Ingestion points: The skill is designed to ingest and analyze external, untrusted PDF files as described in 'Step 1: Classify the Source PDF'.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes or validates the converted output.
  • Capability inventory: The skill utilizes shell execution for tools like pdfinfo, pdftotext, and opendataloader-pdf, and involves writing converted content to files.
  • Sanitization: There are no instructions for sanitizing or filtering the extracted text before the agent uses it for validation or delivery.
  • [COMMAND_EXECUTION]: The skill relies on the execution of several command-line interface (CLI) tools to perform PDF metadata extraction, text layout analysis, and format conversion. The instructions explicitly define the use of pdfinfo, pdftotext, and opendataloader-pdf via shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 01:00 AM
Security Audit — agent-trust-hub — pdf-conversion-router