pyopenms-mass-spectrometry
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to process external data files, such as mzML and FASTA databases, which inherently serves as a surface for indirect prompt injection if those files contain malicious instructions disguised as data.
- Ingestion points: Data is loaded from external files using methods like
ms.MzMLFile().load()andms.FASTAFile().load()as shown in SKILL.md and reference files. - Boundary markers: Not present; the skill does not explicitly instruct the agent to use delimiters or ignore instructions found within the processed files.
- Capability inventory: The skill is restricted to file I/O, mass spectrometry data processing, and visualization. No capabilities for network communication, subprocess execution, or administrative tasks are demonstrated.
- Sanitization: No explicit validation or sanitization of metadata or string content from the input files is shown in the provided code examples.
Audit Metadata