The Agent Skills Directory

[SAFE]: The skill provides legitimate documentation and code samples for the Seaborn data visualization library. It correctly identifies dependencies and uses standard installation practices.
[INDIRECT_PROMPT_INJECTION]: The skill documentation includes examples of ingesting external data, which is a standard surface for indirect prompt injection attacks. However, this is inherent to the library's primary function and no malicious intent was found.
Ingestion points: Use of pd.read_csv and sns.load_dataset for data processing in SKILL.md and references/examples.md.
Boundary markers: The skill does not define specific boundaries or ignore-instructions for processed data content.
Capability inventory: The skill utilizes Bash, Read, Write, and Edit tools for environment management and code execution.
Sanitization: No data sanitization or validation logic is present in the provided examples.

seaborn