The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-supplied gene lists and incorporates them into generated reports, which creates a surface for indirect prompt injection.\n
Ingestion points: SKILL.md (input parameter gene_list) and ora_workflow.md.\n
Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the gene data.\n
Capability inventory: The agent has capabilities to write markdown report files and execute a wide range of analysis tools via the ToolUniverse platform.\n
Sanitization: There are no explicit instructions to sanitize or validate the content of the gene lists before report generation.\n- [EXTERNAL_DOWNLOADS]: The skill documentation correctly identifies and recommends the installation of standard, well-known Python libraries such as gseapy, pandas, scipy, and statsmodels from official package registries.\n- [CREDENTIALS_UNSAFE]: The skill includes a .env.template file that promotes the secure management of API keys through environment variables, which is a standard security best practice.

tooluniverse-gene-enrichment