The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of mass spectrometry output files (e.g., MaxQuant, Spectronaut, DIA-NN outputs).
Ingestion points: External data is loaded in SKILL.md through functions like load_maxquant_proteins and analyze_phosphosites, which read files such as proteinGroups.txt and Phospho (STY)Sites.txt using pandas.
Boundary markers: The instructions do not specify the use of delimiters or specific 'ignore instructions' warnings when processing string-based metadata (e.g., Fasta headers, Gene names) from these files.
Capability inventory: The skill performs complex data processing using pandas and numpy, generates visualizations with matplotlib and seaborn, and invokes external biological analysis tools via the ToolUniverse API for pathway enrichment (enrichr_enrich) and protein interactions (string_get_interactions).
Sanitization: There is no evidence of sanitization or filtering of text fields within the data files before they are processed or used in downstream tool calls.

tooluniverse-proteomics-analysis