alterlab-matplotlib
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests data for visualization and allows output to user-defined file paths.
- Ingestion points: Command-line arguments in
scripts/plot_template.pyandscripts/style_configurator.pyfor plot types, output filenames, and style configurations. - Boundary markers: Absent; the skill relies on the agent to structure the interaction correctly.
- Capability inventory: The skill can write files to the local file system (plots and style sheets) and perform complex data processing using NumPy and SciPy.
- Sanitization: Employs standard library tools like
argparsefor basic input validation and choice restriction. - [SAFE]: External links and references target official documentation and trusted sources (e.g., matplotlib.org).
- [SAFE]: All identified Python dependencies (Matplotlib, NumPy, SciPy) are standard, well-known packages used for their intended scientific purposes.
Audit Metadata