senior-data-scientist
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes Python scripts designed to process data from external files, which introduces a potential surface for indirect prompt injection if the input data contains malicious instructions targeting the agent's logic.
- Ingestion points: The scripts
scripts/experiment_designer.py,scripts/feature_engineering_pipeline.py, andscripts/model_evaluation_suite.pyall accept external file paths via the--inputcommand-line argument. - Boundary markers: There are no instructions or delimiters provided to the agent to distinguish between data content and processing instructions within the ingested files.
- Capability inventory: The scripts are configured to write results to output paths (
--output) and the skill description outlines capabilities for complex data-driven decision making and model evaluation. - Sanitization: The boilerplate code provided does not include logic for sanitizing or validating the content of the input files before processing.
Audit Metadata