The Agent Skills Directory

[SAFE]: The skill is entirely instructional, outlining best practices for biological data analysis such as Gene Ontology enrichment and protein-protein interaction network construction. No malicious patterns, obfuscation, or sensitive data access were identified.
[NO_CODE]: The skill does not contain any code blocks, scripts, or executable commands. It provides guidance on using external bioinformatics tools (e.g., DESeq2, Seurat, Cytoscape) without performing installations or executions itself.
[PROMPT_INJECTION]: The skill is designed to process user-provided biological data such as gene lists and omics results, which represents a surface for indirect prompt injection. However, the skill has no actionable capabilities (file system access, network connectivity, or shell execution) that could be exploited through this data ingestion.
Ingestion points: Gene sets, biological pathways, and multi-omics data (SKILL.md)
Boundary markers: None present
Capability inventory: None; no scripts or tool calls are defined in the skill
Sanitization: No input validation or sanitization procedures are specified

bioinformatics