The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external biological data files, creating a surface for indirect prompt injection. Ingestion points: The run_enrichment.py script reads gene lists and expression results from text and CSV files. Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore instructions embedded within these data sources. Capability inventory: The skill can perform network requests to APIs and write files to the local file system. Sanitization: Minimal; while the script normalizes gene symbol casing and validates numeric types, it does not filter for potential instruction injection.
[EXTERNAL_DOWNLOADS]: The skill fetches gene-set libraries and statistical data from well-known bioinformatics services including Enrichr, g:Profiler, and MSigDB. These connections are standard for the skill's primary purpose and involve established scientific databases.

pathway-enrichment