The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill involves ingesting data for visualization, which presents a surface for indirect prompt injection if the source data is malicious or untrusted.
Ingestion points: Data variables and arrays passed to plotting functions such as ax.plot(), ax.scatter(), and ax.imshow() in SKILL.md.
Boundary markers: No specific boundary markers or instructions to disregard embedded commands in data are present.
Capability inventory: The skill demonstrates file-writing capabilities through plt.savefig() in SKILL.md.
Sanitization: There is no mention of input validation or sanitization for the data being processed.
[COMMAND_EXECUTION]: The documentation guides users to execute local Python scripts distributed as part of the skill.
Evidence: SKILL.md provides instructions to run python scripts/plot_template.py and python scripts/style_configurator.py.

matplotlib