pandoc-converter

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/convert.py facilitates document conversion by calling the pandoc binary via subprocess.run. The command is built using a list-based argument structure, which effectively mitigates shell injection risks. Additionally, the installation instructions in SKILL.md suggest standard use of package managers for dependency management.
  • [EXTERNAL_DOWNLOADS]: The documentation in SKILL.md and scripts/convert.py provides instructions for users to install Pandoc and related LaTeX engines from official sources like pandoc.org and miktex.org through system package managers such as brew and apt.
  • [PROMPT_INJECTION]: The skill processes untrusted document content provided by users, which represents a surface for indirect prompt injection. Ingestion points: Input files read via the input_file parameter in scripts/convert.py. Boundary markers: None present to delimit untrusted file content from instructions. Capability inventory: Execution of pandoc via subprocess.run in scripts/convert.py. Sanitization: The wrapper script uses list-based command execution to prevent argument injection, but file content processing depends on Pandoc's internal parsing logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 10:22 AM
Security Audit — agent-trust-hub — pandoc-converter