The Agent Skills Directory

[SAFE]: The skill provides a legitimate interface to the pymatgen scientific library and the Materials Project database for materials analysis and property prediction.\n- [SAFE]: The skill adheres to security best practices for credential management by instructing the use of environment variables for the Materials Project API key (MP_API_KEY).\n- [INDIRECT_PROMPT_INJECTION]: The skill's analysis and conversion scripts ingest external structure files (such as CIF and POSCAR), which serves as an entry point for potential indirect prompt injection attacks.\n
Ingestion points: Structure.from_file() calls in scripts/structure_analyzer.py and scripts/structure_converter.py.\n
Boundary markers: The skill relies on structured scientific file formats for data delimitation without additional instructions to ignore potential embedded commands.\n
Capability inventory: File system read/write access and network communication with the authenticated Materials Project API.\n
Sanitization: Input content is validated by established crystallographic parsers within the pymatgen library, limiting the impact of malformed data.\n- [EXTERNAL_DOWNLOADS]: The skill installs the pymatgen and mp-api packages from public registries and interacts with the established materialsproject.org API service for data retrieval.

pymatgen