The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions facilitate processing untrusted data which presents a surface for indirect prompt injection.
Ingestion points: The skill provides examples for loading external data files using pd.read_csv() in references/examples.md.
Boundary markers: There are no explicit delimiters or instructions provided to separate data from instructions.
Capability inventory: The skill uses Bash, Read, Write, and Edit tools as defined in the allowed-tools section of SKILL.md.
Sanitization: No data validation or sanitization routines are implemented for external inputs.
[EXTERNAL_DOWNLOADS]: The skill performs expected downloads from well-known and trusted sources.
Fetches the seaborn library and its stats extra from the official package registry.
Downloads sample datasets from the official Seaborn repository on GitHub via sns.load_dataset().

seaborn