mineru-pdf

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted PDF files, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: Content is read from PDF files via the 'magic-pdf' CLI and Python API.
  • Boundary markers: No delimiters or instructions are used to isolate the parsed text from the agent's core instructions.
  • Capability inventory: The skill executes shell commands and writes to the local filesystem.
  • Sanitization: The skill does not include mechanisms to sanitize the content extracted from documents.
  • [COMMAND_EXECUTION]: The skill uses the 'magic-pdf' command-line utility for its primary functionality. While necessary for the skill, any execution involving user-controlled paths should be handled with caution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:20 PM