cobrapy
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates the installation of the legitimate 'cobra' library from PyPI using standard package managers. References to external resources like BiGG and BioModels are standard for systems biology research and represent trusted data sources for metabolic models.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external metabolic model files in SBML, JSON, and YAML formats.
- Ingestion points: External data enters through functions like
read_sbml_modelandload_json_modelinSKILL.mdandreferences/workflows.md. - Boundary markers: The instructions do not define specific delimiters for the content of these models.
- Capability inventory: The skill possesses
BashandWritecapabilities, and scripts perform file-writing operations viato_csvandsavefig. - Sanitization: Validation is performed implicitly by the COBRApy library's parser. While this represents a standard attack surface for data-processing tools, the structured nature of metabolic models makes this a low-risk profile consistent with the skill's primary purpose.
Audit Metadata