microsoft-markitdown

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from various file formats (PDF, Word, Excel, Images, etc.) and external sources like YouTube URLs.
  • Ingestion points: The markitdown command-line tool and Python API ingest user-provided files and remote content from YouTube URLs as described in the workflow.
  • Boundary markers: The instructions lack requirements for using delimiters (like XML tags or markdown blocks) or "ignore embedded instructions" warnings when the agent handles the output of the conversion process.
  • Capability inventory: The skill utilizes the markitdown library which can perform network requests to external services like OpenAI and Azure Document Intelligence for transcription and OCR.
  • Sanitization: No sanitization, escaping, or filtering of the extracted text content is specified before the Markdown result is returned to the agent's context for further processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:16 AM
Security Audit — agent-trust-hub — microsoft-markitdown