skills/plinde/claude-plugins/pandoc/Gen Agent Trust Hub

pandoc

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous examples of executing the 'pandoc' command to convert files, using 'cat' to create temporary files, and 'open' to view outputs. These are standard operations for a document conversion utility.
  • [EXTERNAL_DOWNLOADS]: The instructions suggest installing 'pandoc' and LaTeX engines ('basictex', 'mactex-no-gui') via Homebrew. These are well-known and trusted tools for document processing.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external document files, creating a potential surface for indirect prompt injection.
  • Ingestion points: The skill reads various input files such as input.md and input.docx (SKILL.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present.
  • Capability inventory: The skill utilizes pandoc for conversion, shell commands for style generation, and system tools like brew and open.
  • Sanitization: No evidence of data sanitization or validation of input document content is observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:02 AM