alterlab-pyopenms
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions and reference documents (specifically
references/signal_processing.md) describe the execution of analysis scripts and external command-line tools (TOPP tools) viasubprocessfor specialized tasks like mass calibration.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process various untargeted data formats common in mass spectrometry, creating a potential surface for indirect prompt injection attacks.\n - Ingestion points: Multiple file loaders such as
MzMLFile().load(),FASTAFile().load(), andIdXMLFile().load()are used throughout the skill to import external data.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded content within processed files are provided in the documentation.\n
- Capability inventory: The skill possesses capabilities including file system read/write/edit and the ability to execute shell and Python commands via the
Bashtool.\n - Sanitization: No specific sanitization or validation logic for the content of imported data files is mentioned.
Audit Metadata