matplotlib
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external datasets for visualization and possesses the capability to write files to the disk. * Ingestion points: Untrusted data arrays or DataFrames provided by the user or external files as demonstrated in scripts/plot_template.py and documentation fragments. * Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands within processed data. * Capability inventory: The skill utilizes the Write tool for saving plots (e.g., fig.savefig) and has access to the Bash tool for running Python scripts. * Sanitization: Relies on the underlying Matplotlib and NumPy libraries to validate data structures and shapes during the plotting process.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch bibliographic metadata from the official arXiv repository to facilitate accurate citation of the research library. This targets a well-known and trusted scientific service.
Audit Metadata