The Agent Skills Directory

[SAFE]: The skill provides instructions for installing and using 'gget', a standard open-source bioinformatics package. The installation steps use legitimate Python package managers and the references point to the official Pachter Lab documentation and GitHub repository.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external genomic databases, which constitutes a potential attack surface for indirect prompt injection.
Ingestion points: The skill fetches metadata, sequences, and search results from databases like Ensembl and UniProt through the gget CLI and Python API (referenced in SKILL.md).
Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions in the retrieved biological data.
Capability inventory: The skill enables network operations for database queries and local file writing for saving results across various modules.
Sanitization: The skill does not explicitly describe sanitization of the retrieved genomic data, though the risk is naturally mitigated by the highly structured nature of biological sequences and identifiers.

gget