tikz-figures

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes several Python scripts that use subprocess.run to execute standard technical utilities such as xelatex (for LaTeX compilation), dot (Graphviz, for layout calculation), and pdftoppm (for PDF-to-image conversion). These executions use list-based arguments without a shell, minimizing injection risks, and are essential for the primary purpose of the skill.
  • [EXTERNAL_DOWNLOADS]: The workflow documentation (SKILL.md) instructs the use of uv run to manage Python dependencies. This tool fetches well-known packages like pdfplumber, pymupdf (fitz), and opencv-python-headless from the official Python Package Index (PyPI) registry. These downloads are standard for environment setup and are performed from a well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied figure descriptions to generate TikZ code and refined layouts. It features a complex "visual feedback loop" where output from geometric analysis scripts (in JSON format) is ingested back into the agent's context. While this data path represents an attack surface, the skill emphasizes human-in-the-loop oversight and systematic triaging of detected issues to prevent accidental obedience to any instructions embedded within processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 04:45 PM