tikz-figures

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust workflow for LaTeX/TikZ figure generation. Analysis of the included Python scripts and instructions shows they are dedicated to validating, compiling, and improving the quality of the generated diagrams.
  • [COMMAND_EXECUTION]: Several Python scripts (preview-loop.py, dot-to-tikz.py) use subprocess.run to execute standard system utilities like xelatex, pdftoppm, and Graphviz's dot. These operations are essential for the skill's primary function of rendering and measuring figures.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes uv run to manage Python dependencies (pdfplumber, pymupdf, opencv-python, etc.) for its analysis scripts. These are well-known scientific and PDF processing libraries from official registries.
  • [INDIRECT_PROMPT_INJECTION]: The skill features modes (D and AUDIT) that ingest user-provided .tex files and images for review. While this presents an attack surface for indirect prompt injection, the risk is mitigated by the skill's structured auditing process and is considered low risk in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:43 AM
Security Audit — agent-trust-hub — tikz-figures