tooluniverse-proteomics-analysis
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) due to its processing of untrusted external data files.
- Ingestion points: The skill ingests data from various mass spectrometry output files such as proteinGroups.txt and report.tsv in SKILL.md using pandas.read_csv.
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore embedded instructions within the processed data files.
- Capability inventory: The workflow includes file system access for reading data, statistical processing, and the ability to trigger other internal skills such as tooluniverse-gene-enrichment.
- Sanitization: The skill does not implement validation or sanitization of the input data before it is incorporated into the analysis context.
Audit Metadata