file-converter

Warn

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to dynamically generate and execute Python code at runtime to handle file conversions. This pattern of script generation and execution is a risk factor as it involves assembling executable code based on user requests, which can lead to arbitrary code execution if the generation logic is not strictly constrained.
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its handling of untrusted external data formats.
  • Ingestion points: User-provided files across various formats including PDF, DOCX, Markdown, HTML, JSON, CSV, YAML, and XML.
  • Boundary markers: The skill documentation does not mention the use of delimiters or specific instructions to the agent to disregard natural language instructions found within the source files.
  • Capability inventory: The conversion workflows involve file system read/write operations, image processing via Pillow, and document parsing through numerous specialized libraries.
  • Sanitization: There is no indication of content sanitization, schema validation, or filtering of the input file data before it is processed by the dynamically generated code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:05 PM