pymatgen
Warn
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The references/materials-project.md file contains code examples recommending the use of pickle.load() for caching Materials Project query results. Using pickle to deserialize data is unsafe as it can lead to arbitrary code execution if the input file has been tampered with or comes from an untrusted source.
- [PROMPT_INJECTION]: The skill processes untrusted external materials science files and API data, creating a surface for indirect prompt injection.
- Ingestion points: File reading via Structure.from_file() in references/file-io.md and API data retrieval via MPRester in references/materials-project.md.
- Boundary markers: No specific delimiters or warnings against embedded instructions are provided to the agent.
- Capability inventory: The skill includes capabilities for file system writes, network requests, and executing Python scripts (as seen in examples/structure_analysis_workflow.py).
- Sanitization: No data validation or structural verification is performed on the ingested content.
Audit Metadata