skills/dalehurley/phpbot/markitdown/Gen Agent Trust Hub

markitdown

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by extracting and presenting content from untrusted external files. * Ingestion points: The scripts/convert.py script reads user-specified files and extracts text content using the MarkItDown library. * Boundary markers: Extracted text is returned to the agent without delimiters or instructions to ignore potential commands within the document. * Capability inventory: The skill possesses the ability to execute shell commands (via bash) and Python scripts, which could be leveraged if the agent obeys instructions found within a processed document. * Sanitization: No sanitization or validation is applied to the content extracted from the documents.
  • [EXTERNAL_DOWNLOADS]: The ensure_markitdown function in scripts/convert.py downloads and installs the markitdown[all] package from the official Python Package Index (PyPI) at runtime. This package is maintained by Microsoft, a well-known technology provider.
  • [COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/convert.py to install dependencies and is invoked through shell commands defined in the SKILL.md procedure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:31 AM