tiledbvcf
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download packages from established registries.
- Fetches Python libraries (tiledb-py, tiledbvcf-py, tiledb-cloud, pandas, etc.) from PyPI and Conda channels (conda-forge, bioconda, tiledb).
- Pulls official Docker images from Docker Hub (tiledb/tiledbvcf-py, tiledb/tiledbvcf-cli).
- [COMMAND_EXECUTION]: The skill utilizes shell commands for environment configuration and tool execution.
- Executes conda and mamba for package management and environment setup.
- Uses pip for installing the TileDB-Cloud client.
- Demonstrates the use of the tiledbvcf command-line interface for creating, storing, and exporting genomic data.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection through the ingestion of external data files.
- Ingestion points: Genomic data is ingested from VCF/BCF files via ds.ingest_samples() and CLI store commands (SKILL.md).
- Boundary markers: None identified to differentiate between data and instructions within the processed files.
- Capability inventory: The skill possesses file-system read/write capabilities, network access for cloud storage (S3, Azure, GCS), and the ability to execute subprocesses via CLI tools.
- Sanitization: Relies on the underlying TileDB-VCF library's parsing logic for VCF format validation.
Audit Metadata