matchms
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the 'matchms' Python package and its chemistry-specific dependencies from a package registry using 'uv pip install matchms' and 'uv pip install matchms[chemistry]'.
- [DYNAMIC_EXECUTION]: The documentation identifies 'Pickle' (Python serialization) as a supported format for importing and exporting mass spectrometry data. Loading data from pickle files is a well-known risk for unsafe deserialization, which can be exploited to achieve arbitrary code execution if the agent is directed to process an untrusted file.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files (mzML, MGF, MSP, JSON).
- Ingestion points: Files loaded via functions such as 'load_from_mgf', 'load_from_mzml', 'load_from_msp', and 'load_from_json' (SKILL.md).
- Boundary markers: None identified. The skill does not describe mechanisms to distinguish between data and potentially embedded instructions within spectral files.
- Capability inventory: The skill facilitates file read/write operations and calculations based on ingested data content.
- Sanitization: No explicit sanitization or validation routines for external spectral data are mentioned in the provided documentation.
Audit Metadata