pyopenms
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a set of parameterized CLI tools for mass spectrometry analysis. The code is transparent and uses official scientific libraries (pyOpenMS, Pandas, NumPy) for data processing.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for users to manually download a specific data mapping file (HMDB2StructMapping.tsv) from the official OpenMS GitHub repository if it is missing from the local installation. This is a legitimate scientific resource and the download is not automated.
- [COMMAND_EXECUTION]: Command execution is restricted to running the skill's own scripts via 'uv run python'. These commands are documented and serve standard data analysis purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted mass spectrometry data files (e.g., .mzML, .featureXML).
- Ingestion points: Data is loaded via pyOpenMS file handlers in all analysis scripts.
- Boundary markers: None; scientific data formats are treated as structured input.
- Capability inventory: The skill uses 'Bash', 'Read', 'Write', and 'Edit' tools to process and output analysis results.
- Sanitization: Input data is parsed through strict scientific schemas defined in the pyOpenMS C++ backend; no file content is interpreted as instructional text for the agent.
Audit Metadata