The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or access to sensitive local system files were detected. The network operations are directed at public scientific data repositories.
[Unverifiable Dependencies] (SAFE): Uses the tooluniverse library which appears to be a standard tool orchestration framework for the agent environment. No suspicious package installations or remote script executions were found.
[Indirect Prompt Injection] (LOW): The skill processes data from external sources (ArrayExpress and BioStudies APIs). While these are trusted scientific sources, retrieved metadata should be handled as untrusted data if interpolated into prompts.
Ingestion points: examples.md demonstrates ingestion via arrayexpress_get_experiment_details and biostudies_get_study_details.
Boundary markers: Absent in the provided code examples.
Capability inventory: Data processing and printing; mentions a download tool but does not execute it.
Sanitization: Not explicitly shown in code snippets.

tooluniverse-expression-data-retrieval