giskard-tests
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
giskardpackage from the Python Package Index (PyPI) and references documentation fromlegacy-docs.giskard.ai. - [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and analyzing external machine learning datasets and models, which represents a potential attack surface if the analyzed data contains malicious instructions targeting the ML testing framework.
- Ingestion points: The
raw_dataDataFrame is passed togiskard.DatasetinSKILL.md(Step 2). - Boundary markers: None identified in the provided code snippets.
- Capability inventory: The skill uses
pip installfor package management,to_htmlfor file writing, andSystemExitfor process control in CI environments. - Sanitization: No specific sanitization or validation of the input data is described in the integration steps.
Audit Metadata