single-cell-rna-qc
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external datasets, specifically single-cell RNA data, which represents a potential attack surface.
- Ingestion points: The workflow involves inspecting local files, runtime inputs, and existing conventions.
- Boundary markers: There are no explicit prompt delimiters or "ignore instructions" wrappers specified for the processed data in the instructions.
- Capability inventory: The skill utilizes file system inspection tools and network-enabled tools (
sandbase_run,sandbase_run_get) for external operations. - Sanitization: The instructions mandate "Quality gates" to inspect data shapes, types, units, and missing values before transformation, providing a level of validation for the ingested content.
Audit Metadata