The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided FASTA files and gene lists, which serves as a potential vector for indirect prompt injection attacks. 1. Ingestion points: Data is read from external files in scripts/batch_sequence_analysis.py (read_fasta), scripts/enrichment_pipeline.py (read_gene_list), and scripts/gene_analysis.py (gene symbols). 2. Boundary markers: No explicit delimiters or boundary instructions are used when interpolating file content into logic. 3. Capability inventory: The skill performs extensive network operations to biological databases and writes results to the local file system (CSV and FASTA formats). 4. Sanitization: There is no evidence of sanitization for the genomic sequences or gene symbols before they are processed by the gget library or passed to external APIs.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the gget and openmm packages via the uv tool and manages the download of large scientific datasets, such as the ~4GB AlphaFold model parameters and the ELM database, from established academic and research organizations including Ensembl, NCBI, UniProt, and RCSB PDB.

alterlab-gget