tiledbvcf
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion and processing of genomic variant data (VCF/BCF files), which presents a surface for indirect prompt injection attacks where malicious instructions could be embedded in data fields.\n
- Ingestion points: The skill ingests data through Python methods such as
ds.ingest_samples()andtiledb.cloud.vcf.ingestion.ingest_vcf_dataset(), as well as CLI commands liketiledbvcf storeinSKILL.md.\n - Boundary markers: No explicit delimiters or warnings to ignore embedded instructions were identified in the provided instructions or code examples.\n
- Capability inventory: The skill possesses the capability to write to the file system (
ds.export) and perform network operations to cloud storage (S3, Azure, GCS) and TileDB-Cloud services.\n - Sanitization: No evidence of content sanitization or validation of the VCF data fields was found in the usage patterns.
Audit Metadata