doc-parser

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface detected. The skill parses untrusted external documents (PDF, DOCX, images) and presents their content to the agent context.
  • Ingestion points: The parse_document function in SKILL.md accepts arbitrary file paths to be processed by the docling library.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included when the parsed content is presented to the agent.
  • Capability inventory: The skill possesses file-writing capabilities through the save_tables function which writes CSV files to the local filesystem.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the extracted document content before it is processed or displayed.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the docling package via pip. docling is an official library maintained by IBM, a well-known technology provider, and is considered a safe dependency for document processing tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:44 AM