pdf-processor

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the vendor's orth CLI tool to perform document processing tasks. This is consistent with the author's ecosystem.
  • [PROMPT_INJECTION]: The skill processes external PDF documents, creating an indirect prompt injection surface where instructions embedded in a document could manipulate extraction results.
  • Ingestion points: PDF URLs passed via the website_url and urls fields in the JSON payload of orth api run commands in SKILL.md.
  • Boundary markers: None. There are no instructions provided to the agent or the underlying tools to delimit or ignore instructions found within the document data.
  • Capability inventory: The skill has the capability to run extraction and formatting workflows via the orth tool, calling services like linkup, scrapegraph, and riveter.
  • Sanitization: No content filtering or sanitization of the PDF data is mentioned or implemented before the extraction process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:57 PM