The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for the pandas Python library, focusing on data manipulation, memory management, and performance optimization. All code examples are standard for data science workflows.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for reading external tabular data (e.g., CSV files). While this represents a surface where untrusted data enters the agent's context, the skill does not possess any dangerous capabilities (such as network exfiltration or arbitrary command execution) that would allow for the exploitation of embedded instructions.
Ingestion points: pd.read_csv() in SKILL.md.
Boundary markers: None explicitly defined for file content.
Capability inventory: No subprocess calls, network operations, or dynamic execution patterns are present.
Sanitization: Standard pandas type enforcement (dtype, parse_dates) is recommended.

pandas