bio-reporting-publication-tables
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes well-known, industry-standard libraries for data reporting and formatting. The code examples in 'examples/gene_table_export.py' and 'examples/table1_gtsummary.R' perform local file operations consistent with the skill's stated purpose of table generation.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes data for report generation.
- Ingestion points: Data enters the workflow via 'pandas.DataFrame' and R datasets.
- Boundary markers: No explicit instruction-delimiters are present in the provided templates.
- Capability inventory: The skill possesses file-writing capabilities for multiple formats (XLSX, CSV, DOCX, PNG) on the local system.
- Sanitization: The templates employ library-specific formatting functions like 'fmt_number' and 'fmt_scientific' which provide inherent sanitization for display values. As the skill is intended for static report generation, the risk is minimal.
Audit Metadata