pyopenms
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes mass spectrometry data from external file formats (mzML, idXML, etc.), which establishes an attack surface for indirect prompt injection.
- Ingestion points: Multiple methods in SKILL.md, such as
ms.MzMLFile().load()andms.IdXMLFile().load(), read data from external files into the context. - Boundary markers: No explicit delimiters or instructions to the agent are provided to distinguish between data content and potentially malicious instructions embedded in those files.
- Capability inventory: The skill's capabilities are focused on scientific algorithms and data analysis; it does not contain high-risk operations like arbitrary command execution or network exfiltration.
- Sanitization: There is no evidence of sanitization or validation of text content within the ingested scientific data files.
Audit Metadata