figures-python

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of standard and well-known Python libraries (matplotlib, seaborn, numpy, pandas) from official package registries.
  • [COMMAND_EXECUTION]: Contains instructions for executing Python scripts and managing conda environments, which are necessary for the skill's primary function of data visualization.
  • [PROMPT_INJECTION]: Identified an indirect prompt injection surface where the agent reads data from CSV files to generate plots. 1. Ingestion points: CSV data files in figures/data/. 2. Boundary markers: Not present. 3. Capability inventory: Python script execution using standard libraries. 4. Sanitization: Absent. This data ingestion is required for the skill's primary purpose and does not involve unsafe interpolation into high-risk control paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:57 AM
Security Audit — agent-trust-hub — figures-python