The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were identified in the skill. The logic follows standard scientific data processing workflows using reputable Python libraries.- [EXTERNAL_DOWNLOADS]: The skill references authoritative bioinformatics resources, including HMDB, KEGG, and Reactome, which are well-known and trusted within the research community.- [DATA_EXPOSURE]: The skill reads user-provided metabolomics data (peak tables, spectra) for analysis. This data access is aligned with the skill's primary function and remains within its intended scope.- [PROMPT_INJECTION]: The skill processes external metabolomics data, representing an indirect prompt injection surface. Evidence Chain: 1. Ingestion points: Data is loaded from user-specified file paths using load_metabolomics_data in SKILL.md. 2. Boundary markers: None identified in the provided templates. 3. Capability inventory: File system access and internal platform tool calls via ToolUniverse. 4. Sanitization: Uses standard scientific libraries (pandas, numpy) for data ingestion, which treat values as structured data rather than natural language instructions.

tooluniverse-metabolomics-analysis