The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides utility functions designed to process external datasets via libraries like Pandas and Scikit-learn. While ingesting untrusted data represents an attack surface for indirect prompt injection, the skill lacks high-risk capabilities such as network exfiltration, arbitrary command execution, or persistent file writes, effectively neutralizing the risk.
[EXTERNAL_DOWNLOADS]: The skill mentions common, reputable data science libraries (e.g., NumPy, Pandas, Scikit-learn) in its documentation. No unauthorized or suspicious third-party package installations or remote script executions are present.

data-science